Intelligent automatic door sound control method and system

Abstract

The application provides a kind of intelligent automatic door sound control method and system, it is related to intelligent control technical field.The method includes the voiceprint control data of authorized object is collected, and voiceprint control database is established;Real-time voice control detection data is obtained and is combined with voiceprint control database to carry out object identification based on voiceprint feature, and real-time target object is determined;Object sound control feature information extracted in voiceprint control database is combined with real-time voice control detection data to carry out matching analysis based on object feature, and object matching analysis result data is formed;According to object matching analysis result data, control analysis is carried out, and object sound control data is formed.The method is extracted by using intelligent technology to the sound data of the automatic door needing control, and effective and accurate comparison identification is carried out, and then the high recognition control effect of automatic door based on sound data is realized, and the application range and scene of automatic door are effectively expanded.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent control, in particular to an intelligent automatic door sound control method and system. BACKGROUND

[0002] With the progress of society and the development of science, intelligent control technology is becoming more and more mature, and is gradually applied in various industries, greatly facilitating people's life and work needs. At present, the control of automatic doors usually relies on infrared sensors, microwave radars or pressure sensors to detect the approach of human bodies or objects, thereby triggering the switch. However, these methods have limitations in certain scenarios, such as the inability to recognize specific sound instructions or the inability to distinguish between different user voice requirements. This results in a significant lack of convenience and recognition in the use of automatic doors.

[0003] Intelligent technology has been able to achieve accurate feature information acquisition of sound, so if the control of automatic doors can be based on sound data, the use of automatic doors will be greatly improved, making the use of automatic doors more widespread.

[0004] Therefore, an intelligent automatic door sound control method and system is designed, which extracts features from sound data that needs to control the automatic door and accurately compares and identifies the sound data, thereby achieving high recognition control of the automatic door based on sound data. This effectively expands the scope and scenarios of the automatic door, and is a problem that needs to be solved at present. SUMMARY

[0005] The present application aims to provide an intelligent automatic door sound control method, which collects the voiceprint control data of authorized objects that need to control the automatic door, establishes a voiceprint control database for these authorized objects, and provides sufficient and accurate reference comparison data for subsequent comparison and analysis to identify which authorized object wants to control the automatic door in real time. Based on the real-time voice control detection data of unknown objects, the voiceprint control database is used for voiceprint feature object recognition and object feature matching verification, thereby accurately determining whether the real-time control information is provided by an authorized object. On the one hand, it plays a role in verifying the identity of the real-time object, ensuring that the intelligent control of the automatic door has good object recognition, and on the other hand, it mainly controls the sound data intelligently, expanding the way of controlling the automatic door, further expanding the scope and scenarios of the automatic door, and facilitating the application and promotion of automatic door intelligent control.

[0006] The application also aims to provide an intelligent automatic door sound control system, which comprises a simple and accurate real-time sound detection data acquisition system formed by two pickup microphones arranged in a vertical linear array and a ranging sensor, thereby ensuring the sufficiency and accuracy of sound detection data information acquisition.

[0007] In the first aspect, the application provides an intelligent automatic door sound control method, which comprises: collecting voiceprint control data of authorized objects and establishing a voiceprint control database; acquiring real-time voice control detection data, extracting real-time voice control information in the real-time voice control detection data, and performing object recognition based on voiceprint features in combination with the voiceprint control database to determine a real-time target object; extracting object voice control feature information matched with the real-time target object from the voiceprint control database, and performing matching analysis based on object features in combination with real-time voice detection information in the real-time voice control detection data to form object matching analysis result data; and performing control analysis according to the object matching analysis result data to form object voice control data.

[0008] In the application, the voiceprint control data of authorized objects that need to control the automatic door is collected, and a voiceprint control database for these authorized objects is established, thereby providing sufficient and accurate reference comparison data for subsequent comparison analysis to identify which authorized object wants to control the automatic door in real time. Based on the real-time voice control detection data of unknown objects, the voiceprint control database is used to perform object recognition based on voiceprint features and matching verification of object features, thereby accurately determining whether the real-time control information is provided by an authorized object. On the one hand, it plays a role in verifying the identity of the real-time object, ensuring that the intelligent control of the automatic door has good object recognition, and on the other hand, it mainly combines sound data for intelligent control, expands the mode of automatic door control, further expands the application range and scene of the automatic door, and is conducive to the application and promotion of the intelligent control of the automatic door.

[0009] As a possible implementation, the voiceprint control data of the authorized object is collected, and a voiceprint control database is established, including: extracting object control voice word sets of different authorized objects according to voiceprint control data of different authorized objects; corresponding different object voices in the object control voice word set corresponding to the authorized object with the control instruction word to form an object voice word control mapping table; obtaining the object voice height of different authorized objects and the object voice word control mapping table to form object sound control feature information; extracting the set pronunciation information of different authorized objects, performing voiceprint feature extraction to form corresponding object voiceprint feature information, wherein the object voiceprint feature information includes but is not limited to vibration frequency feature information, pronunciation habit feature information; collecting the object sound control feature information and the object voiceprint feature information corresponding to different authorized objects to form a voiceprint control database.

[0010] In the present application, the voiceprint control data of the authorized object is analyzed and extracted to establish a voiceprint control database, and the main extracted data information includes three aspects: one is the voice word of the authorized object issuing instruction information under different working modes of the automatic door. It can be understood that for different authorized objects, there will be differences in the environment, which will lead to different instructions for the working mode of the same door. For example, for the door opening instruction, some people are used to using "open the door" to express, and some people are used to using "open the door" to express. Therefore, different authorized objects have different habits in voice word collection. Of course, in order to make the control of the door more flexible, each authorized object can provide multiple voice words for any one control instruction, and finally the mapping table is formed to realize the correspondence between the voice word and the control instruction, so as to ensure that the control will not be chaotic due to the complexity of the correspondence. The second aspect is the object voice height. It should be noted that the object voice height is taken as feature information in the present application. One is to provide a reference for subsequent verification of whether the real-time object is an authorized object based on the physical characteristics of the authorized object, so as to avoid the case that the real-time object provides correct voice information conforming to the characteristics of the authorized object, but the sound source is not provided by the real object, thereby improving the safety of the voice feature analysis and verification to a certain extent. Another is to consider that the height data can be used for auxiliary analysis when determining the direction of the sound source, so as to realize accurate direction positioning and object recognition. The third aspect is the voiceprint feature information. The voiceprint feature information contains the individual voice feature information of the authorized object itself, mainly the frequency data of the object with characteristics or unique characteristics, such as pause, stress, pronunciation speed and the like. It can be understood that the more aspects and contents covered by the voiceprint data, the higher the accuracy and precision of the analysis using the voiceprint feature when identifying the object in the later stage. Therefore, the specific feature information contained in the voiceprint feature data can be determined according to the actual situation. Through the extraction of the data of the three aspects, sufficient and comprehensive feature data information for identifying and judging whether the real-time object is an authorized object can be formed.

[0011] As a possible implementation manner, the real-time voice control detection data is acquired, real-time voice control information in the real-time voice control detection data is extracted, and object recognition based on voiceprint features is performed in combination with the voiceprint control database to determine the real-time target object, including: real-time voiceprint feature information is extracted according to the real-time voice control information, and voiceprint feature recognition analysis is performed in combination with object voiceprint feature information of different authorized objects in the voiceprint control database to form a voiceprint feature recognition analysis result; real-time voice words in the real-time voice control information are extracted according to the voiceprint feature recognition analysis result, and voice word recognition analysis is performed in combination with an object voice word control mapping table of different authorized objects in the voiceprint control database to form a voice word recognition analysis result; and an authorized object determined by the voice word recognition analysis result is determined as the real-time target object.

[0012] In the present application, to determine whether the identity of the target object is an authorized object, the real-time voice control detection data needs to be compared and analyzed with voiceprint feature control data of all authorized objects in the voiceprint control database. The main analysis includes recognition of voiceprint features. Since the uniqueness of voiceprint features can quickly determine whether the real-time voice data is of an authorized object, and then the matching of words by real-time voice words is used to determine whether the real-time voice words provide the instruction words for controlling the automatic door corresponding to the authorized object. Only when both the voiceprint feature information and the voice words are matched can it be determined that the real-time object is an authorized object.

[0013] As a possible implementation manner, real-time voiceprint feature information is extracted according to real-time voice control information, and voiceprint feature recognition analysis is performed in combination with object voiceprint feature information of different authorized objects in the voiceprint control database to form a voiceprint feature recognition analysis result, including: the following voiceprint feature recognition analysis is performed according to the real-time voiceprint feature information extracted from the real-time voice control information and the object voiceprint feature information of different authorized objects in the voiceprint control database: if the object voiceprint feature information of an authorized object matches the real-time voiceprint feature information, the authorized object is determined as a voiceprint real-time recognition object; and if there is no authorized object whose object voiceprint feature information matches the real-time voiceprint feature information, non-authorized voiceprint information is formed.

[0014] In the present application, the object recognition analysis based on voiceprint features mainly determines whether the real-time voiceprint feature data can match the voiceprint feature data of different authorized objects in the voiceprint control database, and then determines that the authorized object corresponding to the matched voiceprint feature data is the object required to control the automatic door in real time. Here, the object recognition analysis of the voiceprint feature data needs to ensure that different aspects of the voiceprint feature data can be corresponded in the voiceprint feature data of the same authorized object. For the case that is not found, it can be determined that the real-time data collected this time is not provided by an authorized person.

[0015] As a possible implementation, according to the voiceprint feature recognition analysis result, the real-time voice control information is extracted, and the real-time voice word is combined with the object voice word control mapping table of different authorized objects in the voiceprint control database to perform voice word recognition analysis to form a voice word recognition analysis result, including: when the voiceprint feature recognition result determines the voiceprint real-time recognition object, all object control voice words in the object voice word control mapping table corresponding to the voiceprint real-time recognition object are extracted, and the following voice word recognition analysis is combined with the real-time voice word: if there is no object control voice word matching the real-time voice word, non-control word information is formed.

[0016] In the present application, after object recognition based on voiceprint features, the determined authorized object can be further determined to provide in real-time conditions when the object recognition of the voice word is combined with real-time voice control detection data, mainly analyzing and judging whether the real-time collected voice word exists in the voiceprint control database. If there is a corresponding object, it can prove that the voice word provided by the real-time voice control detection data is the feature word corresponding to the correct automatic door control instruction of the authorized object, and basically the authorized object with the voice word is preliminarily determined. It should be noted that when determining whether the real-time target object is an authorized object through feature recognition analysis, the analysis of voiceprint features is mainly considered. Even if the authorized object matching the voiceprint feature is determined first, this can be done. The next step is whether the real-time object provides voice word information for controlling the automatic door. This step-by-step approach can more reasonably and accurately perform feature recognition analysis.

[0017] As a possible implementation, the object sound control feature information matching the real-time target object in the voiceprint control database is extracted, and the real-time voice detection information in the real-time voice control detection data is combined to perform object feature-based matching analysis to form object matching analysis result data, including: based on the real-time voice detection information, the positioning analysis based on the sound collection direction is performed to determine the sound collection direction angle; based on the real-time voice detection information, the real-time detection distance is obtained, and the object feature matching analysis is performed based on the sound collection direction angle and the object sound control feature information to form the object matching analysis result data.

[0018] In the present application, after object recognition analysis, it can be determined that the real-time sound data can correspond to the sound information of the authorized object in the database, but further matching analysis is required to avoid the case that a non-real object provides authorized object sound feature information. Here, the matching analysis mainly determines whether the object providing the real-time sound data is matched with the feature data collected by the authorized object in the height information.

[0019] As a possible implementation manner, the sound collection direction angle is determined according to the real-time voice detection information, including: according to the real-time voice detection information, a first collection time length T1 corresponding to a first sound collection point arranged in a straight line in a vertical direction and a second collection time length T2 corresponding to a second sound collection point are obtained; according to the first collection time length T1, the second collection time length T2 and a collection interval D between the first sound collection point and the second sound collection point, the sound collection direction angle is determined wherein: c is the speed of sound.

[0020] In the present application, the simplest way to analyze and judge the directionality of sound collection is to provide two sound information pickup points, and the time difference of sound information collected by the two pickup points is analyzed to determine the angle relationship in the vertical direction of the two pickup points when the sound source propagates.

[0021] As a possible implementation manner, the real-time detection distance is obtained according to the real-time voice detection information, and the object feature matching analysis is performed in combination with the sound collection direction angle and the object sound control feature information to form the object matching analysis result data, including: according to the object sound control feature information corresponding to the real-time target object, the object sound emission height H corresponding to the real-time target object is extracted; a matching analysis plane coordinate system is established with the vertical direction of the first sound collection point and the second sound collection point as the longitudinal axis; according to the sound collection direction angle and the object sound emission height H of the real-time target object, the sound source direction line segment is determined on the plane coordinate system, and the sound source direction line segment satisfies the following conditions: one end of the sound source direction line segment intersects with the longitudinal axis of the matching analysis plane coordinate system, and the acute angle formed with the longitudinal axis is equal to the sound collection direction angle the vertical distance from the other end of the sound source direction line segment away from the longitudinal axis to the transverse axis of the matching analysis plane coordinate system is equal to the real-time detection distance; according to the determined sound source direction line segment, the projection value of the sound source direction line segment on the transverse axis of the matching analysis plane coordinate system is determined and labeled as the real-time sound source distance; according to the real-time sound source distance and the real-time detection distance, the following matching analysis judgment is performed: if the difference between the real-time sound source distance and the real-time detection distance does not exceed the error allowed distance difference threshold, the real-time target object is normally labeled for sound source position matching; if the difference between the real-time sound source distance and the real-time detection distance exceeds the error allowed distance difference threshold, the real-time target object is abnormally labeled for sound source position matching.

[0022] In the present application, after the angle relationship between the sound source occurrence direction and the vertical direction straight line where the two pickup points are located is obtained, the object authenticity verification can be carried out by using the angle relationship. It should be noted that the object authenticity verification is not a direct result verification of the object sound emission height, but a determination of the distance between the object and the pickup point by means of the object sound emission height, the sound collection direction angle and the triangular relationship of the vertical straight line where the pickup point is located, and then a comparison analysis is carried out by comparing the actual measured distance value to verify it. When talking, due to the existence of sound noise reduction, filtering, data error and other situations, the judgment standard provided when analyzing and judging is the error allowed distance difference threshold value, which can be set according to the actual situation, or can be determined based on big data analysis.

[0023] As a possible implementation manner, according to the object matching analysis result data, control analysis is carried out to form object sound control data, including: for the real-time target object after object feature matching analysis, the matched object control voice word is determined according to the object voice word control mapping table to determine the corresponding control instruction word; according to the determined control instruction word, control instruction information is formed.

[0024] In the present application, of course, after the object recognition and matching verification, it can be determined that the authorized object is real-time controlled to the automatic door, the specific control instruction provided by the real-time sound data is determined through the mapping table, and the control of the automatic door is realized.

[0025] In the second aspect, the present application provides an intelligent automatic door sound control system, which comprises: a first pickup microphone, a second pickup microphone, a distance measuring sensor, a central processing unit and a memory; the first pickup microphone and the second pickup microphone are installed on the door and arranged in a straight line along the vertical direction; the distance measuring sensor is installed on the door, and the central processing unit is connected with the first pickup microphone, the second pickup microphone, the distance measuring sensor and the memory respectively; the memory stores a voiceprint control database established by voiceprint control data of different authorized objects and a collection interval of the first pickup microphone and the second pickup microphone in the vertical direction; the central processing unit collects real-time voice control detection data from the first pickup microphone and the second pickup microphone, and carries out feature recognition and matching analysis with the voiceprint control database and the collection interval extracted from the memory to form object sound control data.

[0026] In the application, the system is composed of two pickup microphones arranged in vertical linear arrangement and distance measuring sensors, which is simple and can accurately obtain real-time sound detection data, and the sufficiency and accuracy of sound detection data information collection are ensured, the central processor performs comparative analysis and verification on all obtained data and extracted and stored characteristic data, different functional modules are closely linked to form an organic whole capable of efficiently and accurately controlling the intelligent automatic door, and each module is closely linked, which is an important material basis for completing the intelligent automatic door sound control.

[0027] The application provides an intelligent automatic door sound control method and system.

[0028] The method collects voiceprint control data of authorized objects needing to control the automatic door, establishes a voiceprint control database for the authorized objects, and provides sufficient and accurate reference comparison data for subsequent comparison and analysis to identify which authorized object wants to control the automatic door in real time. Based on the real-time voice control detection data of unknown objects, the voiceprint control database is used for voiceprint feature object recognition and object feature matching verification, and it is accurately determined whether the real-time control information is provided by the authorized object. On the one hand, the real-time object identity is verified, and the object recognition of the intelligent control of the automatic door is ensured. On the other hand, the automatic door is intelligently controlled in combination with the sound data, the mode of controlling the automatic door is expanded, the application range and scene of the automatic door are further expanded, and the application and popularization of the intelligent control of the automatic door are facilitated.

[0029] The system is composed of two pickup microphones arranged in vertical linear arrangement and distance measuring sensors, which is simple and can accurately obtain real-time sound detection data, and the sufficiency and accuracy of sound detection data information collection are ensured, the central processor performs comparative analysis and verification on all obtained data and extracted and stored characteristic data, different functional modules are closely linked to form an organic whole capable of efficiently and accurately controlling the intelligent automatic door, and each module is closely linked, which is an important material basis for completing the intelligent automatic door sound control. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments of the application. It should be understood that the following drawings only show some embodiments of the application, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0031] Fig. 1 The steps of the intelligent automatic door sound control method provided by the embodiments of the application are shown in the figure.

[0032] Fig. 2 A structural schematic diagram of an intelligent automatic door sound control system provided by an embodiment of the present application is shown in the figure.

[0033] Fig. 3 A data relationship diagram of object matching analysis of an intelligent automatic door sound control method provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings.

[0035] With the progress of society and the development of science, intelligent control technology is becoming more and more mature, and is gradually applied in various industries, greatly facilitating people's life and work needs. At present, the control of automatic doors usually relies on infrared sensors, microwave radars or pressure sensors to detect the approach of human bodies or objects, thereby triggering the switch. However, these methods have limitations in certain scenarios, such as the inability to recognize specific sound instructions or the inability to distinguish the voice needs of different users. This results in a great deficiency in the convenience and recognition of automatic doors.

[0036] Intelligent technology has been able to achieve accurate feature information acquisition of sound, so if the control of automatic doors can be realized based on intelligent control of sound data, it will greatly improve the use function of automatic doors, making the use of automatic doors more extensive.

[0037] Reference Figs. 1-3 The embodiments of the present application provide an intelligent automatic door sound control method, which collects voiceprint control data of authorized objects that need to control the automatic door, establishes a voiceprint control database for these authorized objects, and further provides sufficient and accurate reference comparison data for subsequent comparison and analysis to identify which authorized object wants to control the automatic door in real time. Based on the real-time voice control detection data of unknown objects, the voiceprint control database is used for voiceprint feature object recognition and object feature matching verification, and then it is accurately determined whether the real-time control information is provided by an authorized object. On the one hand, it plays a role in verifying the identity of the real-time object, ensuring that the intelligent control of the automatic door has good object recognition, and on the other hand, it mainly combines sound data for intelligent control, expands the mode of automatic door control, further expands the application range and scene of the automatic door, and is conducive to the application and promotion of automatic door intelligent control.

[0038] The intelligent automatic door sound control method specifically includes the following steps:

[0039] S1: Collect voiceprint control data of authorized objects, and establish a voiceprint control database.

[0040] The voiceprint control data of the authorized object is collected, and a voiceprint control database is established, including: extracting object control voice word sets of different authorized objects according to voiceprint control data of different authorized objects; corresponding different object voices in the object control voice word set corresponding to the authorized object with the control instruction word to form an object voice word control mapping table; obtaining the object voice height of different authorized objects and the object voice word control mapping table to form object sound control feature information; extracting the set pronunciation information of different authorized objects, performing voiceprint feature extraction to form corresponding object voiceprint feature information, wherein the object voiceprint feature information includes but is not limited to vibration frequency feature information, pronunciation habit feature information; the object sound control feature information and the object voiceprint feature information corresponding to different authorized objects are collected to form a voiceprint control database.

[0041] The voiceprint control database is established by analyzing and extracting the voiceprint control data of the authorized object. The main extracted data information includes three aspects. One is the voice word of the authorized object issuing instruction information under different working modes of the automatic door. It can be understood that for different authorized objects, there are differences in their respective environments, which leads to different instructions for the working mode of the same door. For example, for the door opening instruction, some people are used to using "open the door" to express, and some people are used to using "open the door" to express. Therefore, different authorized objects have different habits in voice word collection. Of course, in order to make the control of the door more flexible, each authorized object can provide multiple voice words for any one control instruction. Finally, the mapping table is formed to realize the correspondence between the voice word and the control instruction, so as to ensure that the control will not be chaotic due to the complexity of the correspondence. The second aspect is the object voice height. It needs to be explained that the object voice height is taken as feature information in the present application. One is to provide a reference for subsequent verification of whether the real-time object is an authorized object based on the physical characteristics of the authorized object, so as to avoid the case that the real-time object provides correct voice information conforming to the characteristics of the authorized object, but the sound source is not the real object, which improves the safety of voice feature analysis and verification to a certain extent. Another is to consider that this height data can be used for auxiliary analysis when determining the direction of the sound source, so as to realize accurate direction positioning and object recognition. The third aspect is the voiceprint feature information. The voiceprint feature information contains individual voice feature information of the authorized object. It mainly includes frequency data of the object with characteristics or unique characteristics, such as pause, stress, pronunciation speed and the like. It can be understood that the more aspects and contents covered by the voiceprint data, the higher the accuracy and precision of the analysis using the voiceprint feature when identifying the object in the later stage. Therefore, the specific feature information contained in the voiceprint feature data can be determined according to the actual situation. Through the extraction of the data of the three aspects, sufficient and comprehensive feature data information for identifying and judging whether the real-time object is an authorized object can be formed.

[0042] S2: Obtain real-time voice control detection data, extract real-time voice control information in the real-time voice control detection data, and perform object recognition based on voiceprint features in combination with a voiceprint control database to determine a real-time target object.

[0043] Obtaining real-time voice control detection data, extracting real-time voice control information in the real-time voice control detection data, and performing object recognition based on voiceprint features in combination with a voiceprint control database to determine a real-time target object, comprises: extracting real-time voiceprint feature information according to real-time voice control information, and performing voiceprint feature recognition analysis in combination with object voiceprint feature information of different authorized objects in the voiceprint control database to form a voiceprint feature recognition analysis result; extracting real-time voice words in the real-time voice control information according to the voiceprint feature recognition analysis result, and performing voice word recognition analysis in combination with an object voice word control mapping table of different authorized objects in the voiceprint control database to form a voice word recognition analysis result; determining an authorized object determined by the voice word recognition analysis result as the real-time target object.

[0044] To determine whether the identity of the target object is an authorized object, real-time voice control detection data needs to be compared and analyzed with voiceprint feature control data of all authorized objects in the voiceprint control database. The main analysis includes recognition of voiceprint features. Since the uniqueness of voiceprint features can quickly determine whether real-time voice data is an authorized object, and then the matching of words by real-time voice words is used to determine whether the real-time voice words provide the command words for controlling the automatic door corresponding to the authorized object. Only when both the voiceprint feature information and the voice words match can it be determined that the real-time object is an authorized object.

[0045] According to real-time voice control information, extracting real-time voiceprint feature information, and performing voiceprint feature recognition analysis in combination with object voiceprint feature information of different authorized objects in the voiceprint control database to form a voiceprint feature recognition analysis result, comprises: performing the following voiceprint feature recognition analysis according to real-time voiceprint feature information extracted from real-time voice control information and object voiceprint feature information of different authorized objects in the voiceprint control database: if there is an authorized object whose object voiceprint feature information matches the real-time voiceprint feature information, the authorized object is determined as a voiceprint real-time recognition object; if there is no authorized object whose object voiceprint feature information matches the real-time voiceprint feature information, non-authorized voiceprint information is formed.

[0046] The object recognition analysis based on the voiceprint feature is mainly to determine whether the real-time voiceprint feature data can match the voiceprint feature data of different authorized objects in the voiceprint control database, and then determine the authorized object corresponding to the matched voiceprint feature data as the object required to control the automatic door in real time. Here, the object recognition analysis of the voiceprint feature data needs to ensure that different aspects of the voiceprint feature data can be corresponded in the voiceprint feature data of the same authorized object. For the case not found, it can be determined that the real-time data collected this time is not provided by the authorized personnel.

[0047] According to the voiceprint feature recognition analysis result, the real-time voice word in the real-time voice control information is extracted, and the voice word recognition analysis is performed in combination with the object voice word control mapping table of different authorized objects in the voiceprint control database to form a voice word recognition analysis result, including: when the voiceprint feature recognition result determines the voiceprint real-time recognition object, all object control voice words in the object voice word control mapping table corresponding to the voiceprint real-time recognition object are extracted, and the following voice word recognition analysis is performed in combination with the real-time voice word: if there is an object control voice word matching the real-time voice word, the voiceprint real-time recognition object is determined as the voice word real-time recognition object; if there is no object control voice word matching the real-time voice word, non-control word information is formed.

[0048] After the object recognition based on the voiceprint feature, it can be further determined that the authorized object determined in real time provides the object recognition of the voice word in combination with the real-time voice control detection data, which mainly analyzes and judges whether the real-time collected voice word exists in the voiceprint control database. If there is, it can be proved that the voice word provided by the real-time voice control detection data is the feature word corresponding to the correct automatic door control instruction of the authorized object, and the authorized object with the voice word is basically determined. It should be noted that when determining whether the real-time target object is an authorized object through feature recognition analysis, the analysis of the voiceprint feature is mainly considered. Even if the authorized object matching the voiceprint feature is determined first, this can be done. The next step is to determine whether the real-time object provides voice word information for controlling the automatic door. This step-by-step approach can more reasonably and accurately perform feature recognition analysis.

[0049] S3: Extract the object voice control feature information matching the real-time target object in the voiceprint control database, and perform matching analysis based on the object feature in combination with the real-time voice detection information in the real-time voice control detection data to form object matching analysis result data.

[0050] Extract the object sound control feature information matched with the real-time target object in the voiceprint control database, and combine the real-time voice control detection data with the real-time voice detection information to perform object feature-based matching analysis to form object matching analysis result data, including: based on the real-time voice detection information, performing directional positioning analysis based on sound collection to determine the sound collection direction angle; based on the real-time voice detection information, obtaining the real-time detection distance, and combining the sound collection direction angle and the object sound control feature information to perform object feature matching analysis to form the object matching analysis result data.

[0051] After object recognition analysis, it can be determined that the real-time sound data can correspond to the authorized object sound information in the database, but further matching analysis is still needed to avoid the case of providing authorized object sound feature information by a non-real object. Here, the matching analysis mainly determines whether the object providing the real-time sound data is matched with the authorized object feature data in the height information.

[0052] Based on the real-time voice detection information, directional positioning analysis based on sound collection is performed to determine the sound collection direction angle, including: based on the real-time voice detection information, obtaining the first collection time T1 corresponding to the first sound collection point and the second collection time T2 corresponding to the second sound collection point arranged in a straight line in the vertical direction; based on the first collection time T1, the second collection time T2, and the collection interval D between the first sound collection point and the second sound collection point, the sound collection direction angle is determined wherein: c is the speed of sound.

[0053] The simplest way to analyze and determine the directionality of sound collection is to provide two sound information pickup points, and determine the angle relationship between the sound source propagation and the two pickup points in the vertical direction by analyzing the time difference of sound information collected by the two pickup points.

[0054] Based on the real-time voice detection information, the real-time detection distance is obtained, and the sound collection direction angle and the object sound control feature information are combined to perform object feature matching analysis to form object matching analysis result data, including: based on the object sound control feature information corresponding to the real-time target object, the object sound height H corresponding to the real-time target object is extracted; a matching analysis plane coordinate system is established with the vertical direction of the first sound collection point and the second sound collection point as the longitudinal axis; based on the sound collection direction angle and the object sound height H of the real-time target object, the sound source direction line segment is determined on the plane coordinate system, and the sound source direction line segment satisfies the following conditions: one end of the sound source direction line segment intersects with the longitudinal axis of the matching analysis plane coordinate system, and the acute angle formed with the longitudinal axis is equal to the sound collection direction angle The vertical distance from the other end of the sound source direction line segment away from the vertical axis to the horizontal axis of the matching analysis plane coordinate system is equal to the real-time detection distance. Based on the determined sound source direction line segment, the projection value of the sound source direction line segment on the horizontal axis of the matching analysis plane coordinate system is determined and calibrated as the real-time sound source distance. Based on the real-time sound source distance and the real-time detection distance, the following matching analysis judgment is performed: if the difference between the real-time sound source distance and the real-time detection distance does not exceed the error allowable distance difference threshold, the real-time target object is marked as having normal sound source position matching; if the difference between the real-time sound source distance and the real-time detection distance exceeds the error allowable distance difference threshold, the real-time target object is marked as having abnormal sound source position matching.

[0055] After obtaining the angular relationship between the direction of the sound source and the vertical lines of the two pickup points, the object's authenticity can be verified using this angular relationship. It's important to note that object authenticity verification doesn't directly verify the object's sound height. Instead, it uses the trigonometric relationship between the object's sound height, the sound acquisition direction angle, and the vertical line of the pickup points to determine the distance between the object and the pickup points. This distance is then compared with actual measured distance values ​​for verification. However, due to factors such as sound noise reduction, filtering, and data errors, the judgment standard provided during analysis is an allowable distance difference threshold. This threshold can be set based on actual conditions or determined based on big data analysis.

[0056] S4: Based on the object matching analysis results, perform control analysis to generate object voice control data.

[0057] Based on the object matching analysis results, control analysis is performed to generate object voice control data, including: for real-time target objects after object feature matching analysis, determining the corresponding control command words based on the matched object control voice words according to the object voice word control mapping table; and generating control command information based on the determined control command words.

[0058] Of course, after object recognition and matching verification, it can be completely determined that the authorized object controls the automatic door in real time. The specific control instructions provided by the real-time sound data are determined through the mapping table, thereby realizing the control of the automatic door.

[0059] The application further provides an intelligent automatic door sound control system, which comprises a first pickup microphone, a second pickup microphone, a distance measuring sensor, a central processing unit and a memory.

[0060] The system comprises two pickup microphones arranged in a vertical linear array and a distance measuring sensor, which can accurately obtain real-time sound detection data and ensure the sufficiency and accuracy of sound detection data information acquisition.

[0061] In summary, the intelligent automatic door sound control method and system provided by the application have the following advantages:

[0062] The method collects voiceprint control data of authorized objects that need to control the automatic door, establishes a voiceprint control database for the authorized objects, and provides sufficient and accurate reference comparison data for subsequent comparison and analysis to identify which authorized object wants to control the automatic door in real time. Based on the real-time voice control detection data of unknown objects, the voiceprint control database is used for voiceprint feature object recognition and object feature matching verification, so that it can be accurately determined whether the real-time control information is provided by an authorized object. On the one hand, it verifies the identity of the real-time object and ensures that the intelligent control of the automatic door has good object recognition. On the other hand, it mainly controls the automatic door intelligently based on sound data, expands the control mode of the automatic door, further expands the application range and scene of the automatic door, and is conducive to the application and promotion of the intelligent control of the automatic door.

[0063] The system is composed of two pickup microphones in vertical linear arrangement and a ranging sensor, and can accurately acquire real-time sound detection data, thereby ensuring the sufficiency and accuracy of the sound detection data information acquisition. The central processor performs comparison and analysis verification on all acquired data and extracted and stored characteristic data, and closely links different functional modules to form an organic whole capable of efficiently and accurately controlling the intelligent automatic door, and the modules are closely linked to each other and are an important material basis for completing the intelligent automatic door sound control.

[0064] In the embodiments of the present application, the indication can include direct indication and indirect indication, and can also include explicit indication and implicit indication. The information indicated by certain information is referred to as to-be-indicated information, and in the specific implementation process, there are many ways to indicate the to-be-indicated information, for example but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or an index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of each information agreed in advance (for example, a protocol stipulates), thereby reducing the indication overhead to a certain extent. At the same time, the common part of each information can be identified and indicated uniformly, so as to reduce the indication overhead caused by separately indicating the same information.

[0065] In addition, the specific indication manner can also be various existing indication manners, for example but not limited to, the above-mentioned indication manners and various combinations thereof. The specific details of various indication manners can refer to the prior art, and will not be described herein. As can be seen from the above, for example, when multiple information of the same type needs to be indicated, the indication manner of different information can be different. In the specific implementation process, the required indication manner can be selected according to the specific needs, and the selected indication manner is not limited in the embodiments of the present application, so that the indication manner involved in the embodiments of the present application should be understood as covering various methods that can enable the to-be-indicated party to know the to-be-indicated information.

[0066] It should be understood that the to-be-indicated information can be sent as a whole or divided into multiple sub-information and sent separately, and the sending period and / or sending time of the sub-information can be the same or different. The specific sending method is not limited in the embodiments of the present application. The sending period and / or sending time of the sub-information can be pre-defined, for example, pre-defined according to a protocol, or configured by the sending end device by sending configuration information to the receiving end device.

[0067] The predefinition or pre-configuration can be realized by pre-storing corresponding codes, tables or other means for indicating relevant information in the device, and the embodiments of the present application do not limit the specific implementation manner. The storage can be in one or more memories. The one or more memories can be separately arranged or integrated in the encoder or decoder, processor or communication device. The one or more memories can be partially separately arranged and partially integrated in the decoder, processor or communication device. The memory can be any form of storage medium, and the embodiments of the present application do not limit the same.

[0068] The protocol referred to in the embodiments of the present application can refer to a protocol family in the communication field, a standard protocol similar to the protocol family frame structure, or a relevant protocol applied to a future communication system, and the embodiments of the present application do not limit the same.

[0069] In the embodiments of the present application, the descriptions such as "when", "in the case of", "if" and "whether" all refer to that the device will make corresponding processing under certain objective condition, and are not limited in time, and do not require the device to have a judgment action when implemented, nor mean that there are other limitations.

[0070] In the description of the embodiments of the present application, unless otherwise specified, " / " represents that the objects before and after the " / " are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the embodiments of the present application is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, wherein A and B can be singular or plural. In addition, in the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. "At least one of the following" or the like means any combination of the items, including any combination of single item or multiple items. For example, at least one of a, b or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, and c can be single or multiple. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, "first", "second", and the like are used to distinguish the same items or similar items with basically the same function and role. Those skilled in the art can understand that "first", "second", and the like do not limit the quantity and execution order, and "first", "second", and the like do not necessarily mean different. At the same time, in the embodiments of the present application, "exemplary" or "for example" means to take an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, "exemplary" or "for example" is used to present the relevant concept in a specific manner, for understanding.

[0071] It should be understood that the processor in the embodiments of the present application can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0072] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, and not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0073] The above-described embodiments can be implemented in part or in whole through software, hardware (e.g., circuitry), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When loaded and executed by a computer, the computer instructions or computer programs can produce the processes or functions described above in accordance with the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, such as from a website site, a computer, a server, or a data center to another website site, a computer, a server, or a data center through a wired (e.g., infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium or a collection of medium accessible by a computer or a data storage device such as a server, a data center, etc. containing one or more available medium. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0074] It should be understood that the term "and / or" in this document is merely used to describe an associated relationship between associated objects, and can represent three relationships, for example, A and / or B can represent three cases of A alone, A and B together, and B alone, where A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the front and rear associated objects, but can also represent an "and / or" relationship. The specific meaning can be understood according to the context before and after.

[0075] In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0076] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined according to their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0077] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0078] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0079] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0080] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0081] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0082] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0083] 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 can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An intelligent automatic door sound control method, characterized by, The method comprises the following steps: Collecting voiceprint control data of authorized objects to establish a voiceprint control database; Obtaining real-time voice control detection data, extracting real-time voice control information from the real-time voice control detection data, and combining the voiceprint control database to perform object recognition based on voiceprint features to determine a real-time target object; Extracting object voice control feature information matching the real-time target object from the voiceprint control database, and combining real-time voice detection information in the real-time voice control detection data to perform matching analysis based on object features to form object matching analysis result data; According to the object matching analysis result data, performing control analysis to form object voice control data; Wherein, collecting voiceprint control data of authorized objects to establish a voiceprint control database comprises: According to the voiceprint control data of different authorized objects, extracting object control voice word sets of different authorized objects; Corresponding different object voices in the object control voice word set of the authorized object to control instruction words to form an object voice word control mapping table; Obtaining object sound production height of different authorized objects and the object voice word control mapping table to form object voice control feature information; Extracting the set pronunciation information of different authorized objects, performing voiceprint feature extraction to form corresponding object voiceprint feature information, wherein the object voiceprint feature information includes but is not limited to vibration frequency feature information and pronunciation habit feature information; Collecting the object voice control feature information and the object voiceprint feature information corresponding to different authorized objects to form the voiceprint control database.

2. The intelligent automatic door sound control method according to claim 1, wherein The method comprises the following steps: According to the real-time voice control information, extracting real-time voiceprint feature information, and combining the object voiceprint feature information of different authorized objects in the voiceprint control database to perform voiceprint feature recognition analysis to form a voiceprint feature recognition analysis result; According to the voiceprint feature recognition analysis result, extracting real-time voice words in the real-time voice control information, and combining the object voice word control mapping table of different authorized objects in the voiceprint control database to perform voice word recognition analysis to form the voice word recognition analysis result; The authorized object determined by the voice word recognition analysis result is determined as the real-time target object.

3. The intelligent automatic door sound control method according to claim 2, wherein, The method comprises the following steps: According to the real-time voice control information, extracting real-time voiceprint feature information, and combining the object voiceprint feature information of different authorized objects in the voiceprint control database to perform voiceprint feature recognition analysis to form a voiceprint feature recognition analysis result; According to the real-time voiceprint feature information extracted from the real-time voice control information and the object voiceprint feature information of different authorized objects in the voiceprint control database, the following voiceprint feature recognition analysis is performed: If the object voiceprint feature information of the authorized object matches the real-time voiceprint feature information, the authorized object is determined as a voiceprint real-time recognition object; If the object voiceprint feature information of the authorized object does not match the real-time voiceprint feature information, unauthorized voiceprint information is formed.

4. The intelligent automatic door sound control method according to claim 3, wherein, According to the voiceprint feature recognition analysis result, the real-time voice control information is extracted, and voice word recognition analysis is performed in combination with the object voice word control mapping table of different authorized objects in the voiceprint control database, and the voice word recognition analysis result is formed, including: After the voiceprint feature recognition result determines the voiceprint real-time recognition object, all object control voice words in the object voice word control mapping table corresponding to the voiceprint real-time recognition object are extracted, and the following voice word recognition analysis is performed in combination with the real-time voice word: If the object control voice word matches the real-time voice word, the voiceprint real-time recognition object is determined as a voice word real-time recognition object; If the object control voice word does not match the real-time voice word, non-control word information is formed.

5. The intelligent automatic door sound control method according to claim 4, wherein, The object sound control feature information matched with the real-time target object is extracted in the voiceprint control database, and object feature-based matching analysis is performed in combination with the real-time voice detection information in the real-time voice control detection data, and object matching analysis result data is formed, including: According to the real-time voice detection information, sound collection direction-based positioning analysis is performed to determine the sound collection direction angle; According to the real-time voice detection information, the real-time detection distance is obtained, and object feature matching analysis is performed in combination with the sound collection direction angle and the object sound control feature information, and object matching analysis result data is formed.

6. The intelligent automatic door sound control method according to claim 5, wherein, According to the real-time voice detection information, sound collection direction-based positioning analysis is performed to determine the sound collection direction angle, including: According to the real-time voice detection information, a first collection time length corresponding to a first sound collection point arranged in a straight line in a vertical direction is acquired and a second collection time length corresponding to a second sound collection point ; According to the first collection time length , the second collection time length , and the collection interval D between the first sound collection point and the second sound collection point, the sound collection direction angle Θ is determined, wherein: c is the speed of sound.

7. The intelligent automatic door sound control method according to claim 6, wherein, According to the real-time voice detection information, the real-time detection distance is obtained, and object feature matching analysis is performed in combination with the sound collection direction angle and the object sound control feature information, and object matching analysis result data is formed, including: According to the object sound control feature information corresponding to the real-time target object, the object sound emission height H corresponding to the real-time target object is extracted; A matching analysis plane coordinate system is established with the vertical direction of the first sound collection point and the second sound collection point as the longitudinal axis; According to the sound collection direction angleƟ and the object sound emission height H of the real-time target object, a sound source direction line segment is determined on the plane coordinate system, and the sound source direction line segment satisfies the following conditions: One end of the sound source direction line segment intersects with the longitudinal axis of the matching analysis plane coordinate system, and the acute angle formed with the longitudinal axis is equal to the sound collection direction angleƟ; The vertical distance from the other end of the sound source direction line segment away from the longitudinal axis to the transverse axis of the matching analysis plane coordinate system is equal to the real-time detection distance; According to the determined sound source direction line segment, a projection value of the sound source direction line segment on a transverse axis of the matching analysis plane coordinate system is determined, and is labeled as a real-time sound source distance; According to the real-time sound source distance and the real-time detection distance, the following matching analysis judgment is performed: If the difference between the real-time sound source distance and the real-time detection distance does not exceed an error allowed distance difference threshold, the real-time target object is labeled as normal in sound source position matching; If the difference between the real-time sound source distance and the real-time detection distance exceeds the error allowed distance difference threshold, the real-time target object is labeled as abnormal in sound source position matching.

8. The intelligent automatic door sound control method of claim 7, wherein, The control analysis is performed according to the object matching analysis result data, and object sound control data is formed, including: For the real-time target object after the object feature matching analysis, the matched object control voice word is determined to correspond to the control instruction word according to the object voice word control mapping table; Control instruction information is formed according to the determined control instruction word.

9. An intelligent automatic door sound control system using the intelligent automatic door sound control method according to any one of claims 1 to 8, characterized by, Including: A first pickup microphone, a second pickup microphone, a ranging sensor, a central processing unit, and a memory; the first pickup microphone and the second pickup microphone are installed on a door and arranged in a straight line in a vertical direction; the ranging sensor is installed on the door, and the central processing unit is connected with the first pickup microphone, the second pickup microphone, the ranging sensor, and the memory respectively; The memory stores a voiceprint control database established by voiceprint control data of different authorized objects and an acquisition interval of the first pickup microphone and the second pickup microphone in the vertical direction; The central processing unit acquires real-time voice control detection data from the first pickup microphone and the second pickup microphone, and performs feature recognition and matching analysis on the voiceprint control database and the acquisition interval extracted from the memory, to form object sound control data.

Images