Elevator control method, device, electronic device and readable storage medium

Abstract

The present application discloses an elevator control method, device, electronic device and readable storage medium, which belongs to the field of artificial intelligence technology. The method includes: when two elevator call instructions are received within a first preset time period, and the second voice recognition result corresponding to the second elevator call instruction is the same as the first voice recognition result corresponding to the first elevator call instruction, according to other recognition information corresponding to the first elevator call instruction except the recognition information with the highest voice matching score, and / or, according to other recognition information corresponding to the second elevator call instruction except the recognition information with the highest voice matching score, determine the first target recognition result; according to the first target recognition result, control the elevator to respond to the second elevator call instruction. The present application can improve the accuracy of elevator call instruction recognition and improve the operating efficiency of the elevator.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to an elevator control method, device, electronic device and readable storage medium. Background Art

[0002] With the continuous development of voice recognition technology, the demand for voice recognition in different fields is increasing. In order to improve the user experience of taking the elevator, contactless smart elevators based on voice recognition came into being.

[0003] At present, when a user speaks an elevator call in the car, the elevator system can identify the command content based on voice recognition technology and control the elevator operation according to the command content. For example, when the command content is "stop at the sixth floor", the button corresponding to the sixth floor of the elevator will light up, and the elevator will pause when it reaches the sixth floor. However, the recognized command content may be wrong, and the elevator control equipment is usually unable to judge this situation, resulting in elevator operation errors, such as pausing at a floor where it should not pause, or opening the door when it needs to be closed, etc., making the elevator operation efficiency low. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide an elevator control method, device, electronic device and readable storage medium, which can solve the problem of low accuracy in elevator call instruction recognition.

[0005] In a first aspect, an embodiment of the present application provides an elevator control method, comprising:

[0006] When two elevator call instructions are received within a first preset time period, a second voice recognition result of a second elevator call instruction is obtained, and the first elevator call instruction is received before the second elevator call instruction;

[0007] When the second voice recognition result is the same as the first voice recognition result of the first elevator call instruction, determining a first target recognition result according to the first voice recognition information and / or the second voice recognition information;

[0008] According to the first target recognition result, controlling the elevator to respond to the second elevator call instruction;

[0009] Among them, the first voice recognition information is other voice recognition information in the first voice recognition information set except the first voice recognition result, and the first voice recognition information set includes at least one information obtained by voice recognition of the first elevator call instruction; the second voice recognition information is other voice recognition information in the second voice recognition information set except the second voice recognition result, and the second voice recognition information set includes at least one information obtained by voice recognition of the second elevator call instruction.

[0010] In a second aspect, an embodiment of the present application provides an elevator control device, comprising:

[0011] A first recognition module, for obtaining a second voice recognition result of a second elevator call instruction when two elevator call instructions are received within a first preset time period, the first elevator call instruction being received before the second elevator call instruction;

[0012] a first determination module, configured to determine a first target recognition result according to the first voice recognition information and / or the second voice recognition information when the second voice recognition result is the same as the first voice recognition result of the first elevator call instruction;

[0013] a first control module, configured to control the elevator to respond to the second elevator call instruction according to the first target recognition result;

[0014] Among them, the first voice recognition information is other voice recognition information in the first voice recognition information set except the first voice recognition result, and the first voice recognition information set includes at least one information obtained by voice recognition of the first elevator call instruction; the second voice recognition information is other voice recognition information in the second voice recognition information set except the second voice recognition result, and the second voice recognition information set includes at least one information obtained by voice recognition of the second elevator call instruction.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0016] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0017] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect.

[0018] In an embodiment of the present application, when two elevator call instructions are received within a first preset time period, and the speech recognition results of the two elevator call instructions are the same, it can be determined that the current speech recognition result may be wrong, and the target recognition result corresponding to the second elevator call instruction can be determined based on other recognition information of the first elevator call instruction except the recognition information with the highest speech matching score, and / or, other recognition information of the second elevator call instruction except the recognition information with the highest speech matching score. The present application can perceive the possibly wrong speech recognition results, and when the speech recognition results are wrong, eliminate the wrong speech recognition results, determine the instruction content corresponding to the elevator call instruction based on other speech recognition information, and promptly control the elevator to respond, thereby improving the recognition accuracy of the elevator call instruction and thus improving the operation efficiency of the elevator. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of an elevator control method provided by an embodiment of the present application;

[0020] Figure 2 is a structural block diagram of an elevator control device provided in an embodiment of the present application;

[0021] Figure 3 It is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0023] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0024] The elevator control method provided by the embodiment of the present application is described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0025] See also Figure 1 , Figure 1It is one of the flow charts of an elevator control method provided in an embodiment of the present application. It should be noted that the elevator control method can be executed by an elevator control system.

[0026] Step 101: When two elevator call instructions are received within a first preset time period, a second voice recognition result of the second elevator call instruction is obtained, and the first elevator call instruction is received before the second elevator call instruction.

[0027] In specific implementation, the two elevator call instructions are the first elevator call instruction and the second elevator call instruction. The second elevator call instruction is the elevator call instruction received again after the first elevator call instruction is received. The interval between the two elevator call instructions does not exceed the first preset time. It can be understood that the first preset time can be shorter, such as 1 second or 2 seconds or 3 seconds, etc., to limit the time interval between the first elevator call instruction and the second elevator call instruction to be shorter. The user of the first elevator call instruction and the user of the second elevator call instruction can be the same person or different people. It can be understood that the first elevator call instruction and the second elevator call instruction are both audio instructions carrying elevator call keywords detected by the elevator control system in the ambient audio signal. The above-mentioned elevator call keywords can be floor keywords, or keywords such as opening the door and closing the door. The specific details can be determined according to the actual situation, and the embodiments of the present application are not limited here.

[0028] When receiving the second elevator call instruction, the elevator control system may perform voice recognition on the second elevator call instruction to obtain a voice recognition result corresponding to the second elevator call instruction. In one example, the elevator control system includes a voice recognition module, and the voice recognition module is used to perform voice recognition on the received elevator call instruction.

[0029] In an optional embodiment, the elevator control system is preset with an acoustic model, a language model and a decoder, wherein the input of the acoustic model is the acoustic features of the audio corresponding to the second elevator call instruction, such as Mel-Frequency Cepstral Coefficients (MFCC), filter bank (FBANK), etc., and the output of the acoustic model is at least one pronunciation combination corresponding to the audio and the pronunciation matching probability and acoustic matching score of each pronunciation combination, and the acoustic matching score is determined based on the pronunciation matching probability; the input of the language model is at least one pronunciation combination output by the acoustic model, and the output of the language model is at least one recognition information (a combination of characters and words) corresponding to the audio and the language matching probability and language matching score of each recognition information, and the language matching score is determined based on the language matching probability; the decoder constructs a decoding graph in combination with the outputs of the acoustic model and the language model, searches for the optimal matching path, and takes the highest value of the voice matching score as the voice recognition result of the second elevator call instruction.

[0030] It is understandable that the implementation method of voice recognition for the second elevator call instruction is not limited to this. For details, reference may be made to the description of voice recognition in the relevant technology and is not limited here.

[0031] Step 102: When the second voice recognition result is the same as the first voice recognition result of the first elevator call instruction, determine a first target recognition result according to the first voice recognition information and / or the second voice recognition information.

[0032] Among them, the first voice recognition information is other voice recognition information in the first voice recognition information set except the first voice recognition result, and the first voice recognition information set includes at least one information obtained by voice recognition of the first elevator call instruction; the second voice recognition information is other voice recognition information in the second voice recognition information set except the second voice recognition result, and the second voice recognition information set includes at least one information obtained by voice recognition of the second elevator call instruction.

[0033] In actual applications, after the user inputs an elevator call command, the elevator control system will determine the user's intention based on the voice recognition results, and control the elevator to respond to the elevator call command. For example, when the user says "Stop at the sixth floor" in the elevator car, the elevator control system can recognize the floor information "sixth floor" included in the elevator call command, and control the button corresponding to the sixth floor in the elevator car to light up. Normally, users who need to go to the sixth floor will not input elevator calls related to floor selection after confirming that the button corresponding to the sixth floor is lit.

[0034] In an embodiment of the present application, if two elevator call instructions are received in a short period of time, and the speech recognition results obtained for the two elevator call instructions are the same, it means that the elevator responded incorrectly to the first elevator call instruction, causing the user to make a second elevator call. For example, the user says "Stop at the sixth floor" in the car, and the elevator control system recognizes that the floor information corresponding to the elevator call instruction is "the sixteenth floor", and controls the button corresponding to the sixteenth floor in the elevator car to light up. After confirming that the button corresponding to the sixth floor is not lit, the user who needs to go to the sixth floor will enter a similar elevator call instruction such as "Stop at the sixth floor" again, but the floor information corresponding to the elevator call instruction recognized by the elevator control system is still "the sixteenth floor". In this case, the elevator control system may not respond to the second elevator call instruction first, but may re-determine the recognition result corresponding to the second elevator call instruction, that is, the first target recognition result, based on the first speech recognition information and / or the second speech recognition information.

[0035] In specific implementation, when the elevator control system performs voice recognition on the first elevator call instruction or the second elevator call instruction, taking the first elevator call instruction as an example, it usually obtains multiple identification information that may match the first elevator call instruction, and the above multiple identification information is recorded as the first voice recognition information set. Each identification information in the first voice recognition information set corresponds to a voice matching score, and the voice matching score is determined based on the matching probability between the identification information and the first elevator call instruction. In general, the final recognition result of voice recognition is the identification information with the highest voice matching score in the first voice recognition information set.

[0036] In the case where the recognition information with the highest voice matching score is wrong, the correct recognition information may be in other recognition information except the recognition information with the highest voice matching score. For example, the voice recognition information of a certain elevator call command includes "sixteenth floor", "sixth floor", and "twenty-sixth floor", which are arranged from high to low according to the voice matching score. In the case where the "sixteenth floor" with the highest voice matching score is wrong, the "sixth floor" or "twenty-sixth floor" may be correct. Compared with controlling the elevator to respond based on the determined wrong "sixteenth floor", determining the final recognition result based on "sixth floor" or "twenty-sixth floor" has a higher recognition accuracy rate.

[0037] The elevator control system can determine the target recognition result corresponding to the second elevator call instruction based on other voice recognition information except the first voice recognition result in the first voice recognition information set, and / or other voice recognition information except the second voice recognition result in the second voice recognition information set, which is recorded here as the first target recognition result.

[0038] In specific implementation, in an optional embodiment, the elevator control system can determine the first voice recognition information based on the voice matching score of each recognition information in the first voice recognition information set. For example, a first preset range can be preset, and the recognition information with a voice matching score within the first preset range can be determined as the first voice recognition information, and the upper limit value of the first preset range is less than the voice matching score corresponding to the first voice recognition result; or the recognition information with the second highest or third highest voice matching score can be determined as the first voice recognition information. In another optional embodiment, the elevator control system can determine the first voice recognition information based on the acoustic matching score of each recognition information in the first voice recognition information set. The specific details can be determined according to actual needs, and the embodiments of the present application are not limited here.

[0039] It should be noted that the implementation method for determining the second voice recognition information can be adaptively adjusted with reference to the above-mentioned implementation method for determining the first voice recognition information, which will not be described in detail here.

[0040] Step 103: According to the first target recognition result, control the elevator to respond to the second elevator call instruction.

[0041] In specific implementation, the elevator control system can control the elevator to respond to the second elevator call command according to the specific content of the first target recognition result. For example, triggering the floor button to light up, or opening and closing the elevator door, etc., for details, please refer to the description in the relevant technology, which will not be repeated here. In one example, the elevator control system includes an elevator control module, which is used to receive the result obtained by the speech recognition module and control the elevator to respond according to the result.

[0042] In an embodiment of the present application, when two elevator call instructions are received within a first preset time period, and the speech recognition results of the two elevator call instructions are the same, it can be determined that the current speech recognition result may be wrong, and the target recognition result corresponding to the second elevator call instruction can be determined based on other recognition information of the first elevator call instruction except the recognition information with the highest speech matching score, and / or, other recognition information of the second elevator call instruction except the recognition information with the highest speech matching score. The present application can sense possible wrong speech recognition results, and when the speech recognition results are wrong, eliminate the wrong speech recognition results, determine the instruction content corresponding to the elevator call instruction based on other speech recognition information, and promptly control the elevator to respond, thereby improving the recognition accuracy of the elevator call instruction and thus improving the operation efficiency of the elevator.

[0043] Optionally, the first voice recognition information is the information with the second highest voice matching score in the first voice recognition information set; and / or the second voice recognition information is the information with the second highest voice matching score in the second voice recognition information set.

[0044] In this embodiment, the elevator control system can determine the first target recognition result based on the recognition information with the second highest voice matching score corresponding to the two elevator call instructions, so as to further improve the accuracy of instruction recognition.

[0045] In specific implementation, in an optional embodiment, the elevator control system may be preset with an acoustic model and a language model to perform voice recognition on the received elevator call command, the acoustic model may output at least one pronunciation combination corresponding to the elevator call command and the pronunciation matching probability and acoustic matching score of each pronunciation combination, and the language model may output at least one recognition information (a combination of characters or words) corresponding to the elevator call command and the language matching probability and language matching score of each recognition information. The elevator control system may determine the sum of the acoustic matching score and the language matching score corresponding to each recognition information as the voice matching score of the recognition information, and determine the information with the second highest voice matching score based on this.

[0046] After determining the first voice recognition information and / or the second voice recognition information, optionally, three specific implementation methods are included:

[0047] In implementation mode 1, the elevator control system may determine the first target recognition information based on the first voice recognition information. In other words, the elevator control system may determine the first target recognition information based on the recognition information with the second highest voice matching score in the first voice recognition information set.

[0048] In an optional embodiment, the elevator control system may determine the first voice recognition information as the first target recognition result. For example, the elevator call instruction received last time is "Stop at the sixth floor". Assuming that the voice recognition information of the elevator call instruction received last time includes three types, which are "the sixteenth floor", "the sixth floor", and "the twenty-sixth floor" in descending order according to the voice matching scores, the elevator control system may determine "the sixth floor" as the first target recognition result. In another optional embodiment, the elevator control system may recognize the second elevator call instruction again based on the first voice recognition information. For example, during the voice recognition process, the weight coefficient of the first voice recognition information is increased.

[0049] In implementation mode 2, the elevator control system may determine the first target recognition information based on the second voice recognition information. In other words, the elevator control system may determine the first target recognition information based on the recognition information with the second highest voice matching score in the second voice recognition information set.

[0050] In an optional implementation, the elevator control system may determine the second voice recognition information as the first target recognition result. In another optional implementation, the elevator control system may recognize the second elevator call instruction again based on the second voice recognition information.

[0051] In implementation mode three, the elevator control system may determine the first target recognition information based on the first voice recognition information and the second voice recognition information. In an optional implementation mode, the higher voice matching score of the first voice recognition information and the second voice recognition information may be determined as the first target recognition information. Exemplarily, the recognition information with the second highest voice matching score in the previous time is "sixth floor", with a voice matching score of 87 points, and the recognition information with the second highest voice matching score currently is "twenty-sixth floor", with a voice matching score of 83 points. The elevator control system may determine "sixth floor" as the first target recognition result.

[0052] It should be noted that, in other embodiments, the first voice recognition information may also be the information with the second highest acoustic matching score in the first voice recognition information set; and / or, the second voice recognition information may be the information with the second highest acoustic matching score in the second voice recognition information set, which is not limited here.

[0053] Optionally, step 102 includes:

[0054] The second speech recognition information is determined as the first target recognition result.

[0055] In the related art, the speech recognition model can usually be continuously trained and optimized based on each elevator call command received. Then, the recognition information obtained by performing speech recognition on the second elevator call command received later may be better than the recognition information obtained by performing speech recognition on the elevator call command received earlier.

[0056] In this embodiment, the elevator control system can determine the first target recognition result only based on the second voice recognition information. Further, optionally, when the second voice recognition information is unique, the second voice recognition information is determined as the first target recognition result to further improve the accuracy of command recognition. In a specific example, the second voice recognition information is determined based on the voice matching score. Further, the second voice recognition information is the recognition information corresponding to the second elevator call command and having the second highest voice matching score.

[0057] Optionally, step 102 includes:

[0058] A first target recognition result is determined according to the first voice recognition information, the second voice recognition information, the first voice recognition result, and the second voice recognition result.

[0059] In this embodiment, the elevator control system may determine the first target recognition result by combining the first voice recognition result and the second voice recognition result.

[0060] In specific implementation, in an optional embodiment, the elevator control system can calculate the difference between the voice matching score of the first language recognition information and the first voice recognition result based on the voice matching score or the acoustic matching score to determine the first difference, and calculate the difference between the voice matching score of the second language recognition information and the second voice recognition result to determine the second difference, and then further determine the first target recognition result based on the first difference and the second difference. Exemplarily, if the first difference is greater than the second difference, the first voice recognition information is determined as the first target recognition result; if the second difference is greater than the first difference, the second voice recognition information is determined as the first target recognition result; if the first difference is equal to the second difference, optionally, the one with the larger voice matching score between the first language recognition information and the second voice recognition information is determined as the first target recognition result.

[0061] Alternatively, the elevator control system may calculate the ratio of the voice matching score of the first language recognition information to the voice matching score of the first voice recognition result to determine the first ratio, and calculate the ratio of the voice matching score of the second language recognition information to the voice matching score of the second voice recognition result to determine the second ratio, and then further determine the first target recognition result based on the first ratio and the second ratio. Exemplarily, if the first ratio is greater than the second ratio, the first voice recognition information is determined as the first target recognition result; if the second ratio is greater than the first ratio, the second voice recognition information is determined as the first target recognition result; if the first ratio is equal to the second ratio, optionally, the one with the larger voice matching score between the first language recognition information and the second voice recognition information is determined as the first target recognition result.

[0062] It should be noted that, in other embodiments, the elevator control system may also determine the first target recognition result based on the recognition information with the highest acoustic matching score and the recognition information with the second best acoustic matching in the first voice recognition information set, and the recognition information with the highest acoustic matching score and the recognition information with the second best acoustic matching in the second voice recognition information set. The recognition information with the second best acoustic matching may be the recognition information with the second highest acoustic matching score. The specific determination process may be carried out with reference to the description of the above embodiments and will not be repeated here.

[0063] Optionally, step 102 includes:

[0064] When the second voice recognition result is the same as the first voice recognition result of the first elevator call instruction, and the voiceprint feature of the second elevator call instruction matches the voiceprint feature of the first elevator call instruction, the first target recognition result is determined according to the first voice recognition information and / or the second voice recognition information.

[0065] In this embodiment, if the elevator control system recognizes that the voiceprint feature of the second elevator call instruction matches the voiceprint feature of the first elevator call instruction, it can be determined that the same user has input two elevator call instructions consecutively within a short period of time. If the recognition results of these two elevator call instructions are the same, it can be considered that the elevator control system has incorrectly recognized the elevator call instructions twice, and the step of determining the first target recognition result based on the first voice recognition information and / or the second voice recognition information can be executed.

[0066] When the user who issues two elevator calls is limited to the same person, it is possible to avoid the situation where the recognition result is judged incorrectly due to different users having elevator calls. For example, user A says the first elevator call "Stop at the sixth floor" in the elevator car, and the elevator control system recognizes that the floor information corresponding to the elevator call is "sixth floor", and controls the button corresponding to the sixth floor in the elevator car to light up. User B enters the second elevator call "I'm going to the sixth floor", and the elevator control system recognizes that the floor information corresponding to the elevator call is also "sixth floor". If the elevator control system does not perform the voiceprint matching operation, it will perform the operation of determining the first target recognition result according to the first voice recognition information and / or the second voice recognition information, so that the second elevator call is responded incorrectly. After performing the voiceprint matching operation, it can be determined that the two elevator calls are not from the same person. For the second elevator call, the elevator control system can control the elevator to respond according to the recognition result of "sixth floor". For example, after determining that the button corresponding to the sixth floor is lit, the operation of controlling the floor button to light up is no longer performed.

[0067] It should be noted that, in this embodiment, the elevator control system can perform voice recognition on the second elevator call instruction and voiceprint recognition on the second elevator call instruction synchronously or asynchronously, and the execution order of the two steps is not limited herein.

[0068] In this embodiment, in an optional implementation manner, after step 103, the method further includes:

[0069] When a third elevator call instruction is received within a second preset time period after the elevator control responds to the second elevator call instruction, a voiceprint feature of the third elevator call instruction is obtained, and a third voice recognition result corresponding to the third elevator call instruction is obtained;

[0070] When the third voice recognition result is the same as the first target recognition result, and the voiceprint feature of the third elevator call instruction matches the voiceprint feature of the second elevator call instruction, based on the first target recognition result and the second target recognition result, voice recognition is performed again on the third elevator call instruction to obtain a third target recognition result;

[0071] According to the third target recognition result, controlling the elevator to respond to the third elevator call instruction;

[0072] Among them, the second target recognition result is the first speech recognition result or the second speech recognition result.

[0073] In this embodiment, when the user of the first elevator call instruction and the second elevator call instruction is the same person, if, based on the first target recognition result, the elevator is controlled to respond to the second elevator call instruction, and then a third elevator call instruction from the same user is received again, and the recognition result is the first target recognition result, it can be determined that the first target recognition result may still be wrong.

[0074] In this case, optionally, two implementation modes are included:

[0075] In the first implementation mode, the elevator control system may perform voice recognition on the third elevator call instruction again based on the first target recognition result and the second target recognition result to obtain a third target recognition result. That is, in the process of performing voice recognition on the third elevator call instruction again, the voice recognition may be optimized based on the information that the first target recognition result and the second target recognition result are erroneous results, thereby improving the recognition accuracy of the voice recognition on the third elevator call instruction again.

[0076] In this embodiment, optionally, in the process of performing voice recognition again on the third elevator call instruction, hot word suppression can be performed on the first target recognition result and the second target recognition result. Exemplarily, hot words can be set for the acoustic model and / or the language model, and the hot words include the first target recognition result and the second target recognition result, and the weight coefficient of the hot words is set to be less than a preset value, or to be negative, so as to suppress the influence of the first target recognition result and the second target recognition result on the voice recognition result.

[0077] In the second implementation mode, the elevator control system may determine the third target recognition result based on the third voice recognition information and / or the fourth voice recognition information. The third voice recognition information is other voice recognition information in the first voice recognition information set except the first target recognition result and the second target recognition result, and the fourth voice recognition information is other voice recognition information in the second voice recognition information set except the first target recognition result and the second target recognition result.

[0078] This embodiment can refer to the description of the above embodiment, and will not be described again here to avoid repetition.

[0079] It should be noted that the elevator control method provided in the embodiment of the present application can be executed by an elevator control device or a control module in the elevator control device for executing the elevator control method. In the embodiment of the present application, the elevator control device executing the elevator control method is taken as an example to illustrate the elevator control device provided in the embodiment of the present application.

[0080] See also Figure 2 , Figure 2 It is a structural diagram of the elevator control device provided in an embodiment of the present application.

[0081] like Figure 2 As shown, the elevator control device 200 includes:

[0082] A first recognition module 201 is used for obtaining a second voice recognition result of a second elevator call instruction when two elevator call instructions are received within a first preset time period, and the first elevator call instruction is received before the second elevator call instruction;

[0083] A first determination module 202, configured to determine a first target recognition result according to the first voice recognition information and / or the second voice recognition information when the second voice recognition result is the same as the first voice recognition result of the first elevator call instruction;

[0084] A first control module 203, configured to control the elevator to respond to the second elevator call instruction according to the first target recognition result;

[0085] Among them, the first voice recognition information is other voice recognition information in the first voice recognition information set except the first voice recognition result, and the first voice recognition information set includes at least one information obtained by voice recognition of the first elevator call instruction; the second voice recognition information is other voice recognition information in the second voice recognition information set except the second voice recognition result, and the second voice recognition information set includes at least one information obtained by voice recognition of the second elevator call instruction.

[0086] Optionally, the first voice recognition information is the information with the second highest voice matching score in the first voice recognition information set; and / or the second voice recognition information is the information with the second highest voice matching score in the second voice recognition information set.

[0087] Optionally, the first determining module 202 includes:

[0088] The first determining unit is used to determine the second speech recognition information as a first target recognition result.

[0089] Optionally, the first determining module 202 includes:

[0090] A second determining unit, configured to determine a first target recognition result according to the first speech recognition information, the second speech recognition information, the first speech recognition result, and the second speech recognition result;

[0091] The third voice recognition information is the first voice recognition result, and the fourth voice recognition information is the second voice recognition result.

[0092] Optionally, the second determining unit includes:

[0093] A first calculation subunit, configured to calculate a ratio of a speech matching score of the first speech recognition information to a speech matching score of the first speech recognition result, to obtain a first ratio;

[0094] A second calculation subunit, configured to calculate a ratio of a matching score of the second speech recognition information to a speech matching score of the second speech recognition result, to obtain a second ratio;

[0095] The first determination subunit is used to determine a first target recognition result according to the first ratio and the second ratio.

[0096] Optionally, the first determining subunit is specifically configured to:

[0097] determining a larger value of the first ratio and the second ratio;

[0098] When the larger value is the first ratio, determining the first speech recognition information as a first target recognition result;

[0099] When the larger value is the second ratio, the second speech recognition information is determined as the first target recognition result.

[0100] Optionally, the first determining module 202 is specifically configured to:

[0101] When the second voice recognition result is the same as the first voice recognition result of the first elevator call instruction, and the voiceprint feature of the second elevator call instruction matches the voiceprint feature of the first elevator call instruction, the first target recognition result is determined according to the first voice recognition information and / or the second voice recognition information.

[0102] Optionally, the elevator control device 200 further includes:

[0103] a second recognition module, configured to obtain a voiceprint feature of the third elevator call instruction and a third voice recognition result corresponding to the third elevator call instruction when a third elevator call instruction is received within a second preset time period after the elevator control responds to the second elevator call instruction;

[0104] a third recognition module, configured to, when the third voice recognition result is the same as the first target recognition result and the voiceprint feature of the third elevator call instruction matches the voiceprint feature of the second elevator call instruction, perform voice recognition again on the third elevator call instruction based on the first target recognition result and the second target recognition result to obtain a third target recognition result;

[0105] A second control module, configured to control the elevator to respond to the third elevator call instruction according to the third target recognition result;

[0106] Among them, the second target recognition result is the first speech recognition result or the second speech recognition result.

[0107] The elevator control device 200 can achieve the following Figure 1 The various processes of the corresponding method embodiments and the same beneficial effects are achieved, and will not be described again here to avoid repetition.

[0108] The present application also provides an electronic device. Figure 3 The electronic device 300 may include a processor 301, a memory 302, and a computer program 3021 stored in the memory 302 and executable on the processor 301. When the computer program 3021 is executed by the processor 301, Figure 1 Any steps in the corresponding method embodiments and achieving the same beneficial effects will not be repeated here.

[0109] A person skilled in the art can understand that all or part of the steps of implementing the above-mentioned embodiment method can be completed by hardware related to program instructions, and the program can be stored in a readable medium. The present application also provides a readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned Figure 1 Any steps in the corresponding method embodiments can achieve the same technical effect and will not be repeated here to avoid repetition.

[0110] The storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0111] The above is a preferred implementation of the embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An elevator control method, characterized in that: include: When two elevator call instructions are received within a first preset time period, a second voice recognition result of a second elevator call instruction is obtained, and the first elevator call instruction is received before the second elevator call instruction; When the second voice recognition result is the same as the first voice recognition result of the first elevator call instruction, determining a first target recognition result according to the first voice recognition information and / or the second voice recognition information; According to the first target recognition result, controlling the elevator to respond to the second elevator call instruction; The first voice recognition information is other voice recognition information in a first voice recognition information set except the first voice recognition result, and the first voice recognition information set includes at least one information obtained by voice recognition of the first elevator call instruction; the second voice recognition information is other voice recognition information in a second voice recognition information set except the second voice recognition result, and the second voice recognition information set includes at least one information obtained by voice recognition of the second elevator call instruction; Wherein, the user of the first elevator call instruction and the user of the second elevator call instruction are not the same person; The determining of the first target recognition result according to the first voice recognition information and / or the second voice recognition information includes: Determine a first target recognition result according to the first voice recognition information, the second voice recognition information, the first voice recognition result, and the second voice recognition result; The determining a first target recognition result according to the first voice recognition information, the second voice recognition information, the first voice recognition result, and the second voice recognition result includes: Calculating a ratio of a speech matching score of the first speech recognition information to a speech matching score of the first speech recognition result to obtain a first ratio; Calculating a ratio of a voice matching score of the second voice recognition information to a voice matching score of the second voice recognition result to obtain a second ratio; Determining a first target recognition result according to the first ratio and the second ratio; The determining a first target recognition result according to the first ratio and the second ratio includes: determining a larger value of the first ratio and the second ratio; When the larger value is the first ratio, determining the first speech recognition information as a first target recognition result; When the larger value is the second ratio, the second speech recognition information is determined as the first target recognition result.

2. The method according to claim 1, characterized in that: The first voice recognition information is the information with the second highest voice matching score in the first voice recognition information set; and / or the second voice recognition information is the information with the second highest voice matching score in the second voice recognition information set.

3. The method according to claim 1, characterized in that The determining of the first target recognition result according to the first voice recognition information and / or the second voice recognition information includes: The second speech recognition information is determined as the first target recognition result.

4. The method according to claim 1, characterized in that: When the second voice recognition result is the same as the first voice recognition result of the first elevator call instruction, determining a first target recognition result according to the first voice recognition information and / or the second voice recognition information includes: When the second voice recognition result is the same as the first voice recognition result of the first elevator call instruction, and the voiceprint feature of the second elevator call instruction matches the voiceprint feature of the first elevator call instruction, the first target recognition result is determined according to the first voice recognition information and / or the second voice recognition information.

5. The method according to claim 4, characterized in that After controlling the elevator to respond to the second elevator call instruction according to the first target recognition result, the method further includes: When a third elevator call instruction is received within a second preset time period after the elevator control responds to the second elevator call instruction, a voiceprint feature of the third elevator call instruction is obtained, and a third voice recognition result corresponding to the third elevator call instruction is obtained; When the third voice recognition result is the same as the first target recognition result, and the voiceprint feature of the third elevator call instruction matches the voiceprint feature of the second elevator call instruction, based on the first target recognition result and the second target recognition result, voice recognition is performed again on the third elevator call instruction to obtain a third target recognition result; According to the third target recognition result, controlling the elevator to respond to the third elevator call instruction; Among them, the second target recognition result is the first speech recognition result or the second speech recognition result.

6. An elevator control device, characterized in that: include: A first recognition module, for obtaining a second voice recognition result of a second elevator call instruction when two elevator call instructions are received within a first preset time period, the first elevator call instruction being received before the second elevator call instruction; a first determination module, configured to determine a first target recognition result according to the first voice recognition information and / or the second voice recognition information when the second voice recognition result is the same as the first voice recognition result of the first elevator call instruction; a first control module, configured to control the elevator to respond to the second elevator call instruction according to the first target recognition result; The first voice recognition information is other voice recognition information in a first voice recognition information set except the first voice recognition result, and the first voice recognition information set includes at least one information obtained by voice recognition of the first elevator call instruction; the second voice recognition information is other voice recognition information in a second voice recognition information set except the second voice recognition result, and the second voice recognition information set includes at least one information obtained by voice recognition of the second elevator call instruction; Wherein, the user of the first elevator call instruction and the user of the second elevator call instruction are not the same person; The first determining module comprises: A second determining unit, configured to determine a first target recognition result according to the first speech recognition information, the second speech recognition information, the first speech recognition result, and the second speech recognition result; The second determining unit includes: A first calculation subunit, configured to calculate a ratio of a speech matching score of the first speech recognition information to a speech matching score of the first speech recognition result, to obtain a first ratio; A second calculation subunit, configured to calculate a ratio of a matching score of the second speech recognition information to a speech matching score of the second speech recognition result, to obtain a second ratio; A first determining subunit, configured to determine a first target recognition result according to the first ratio and the second ratio; The first determining subunit is specifically used for: determining a larger value of the first ratio and the second ratio; When the larger value is the first ratio, determining the first speech recognition information as a first target recognition result; When the larger value is the second ratio, the second speech recognition information is determined as the first target recognition result.

7. An electronic device, characterized in that: The method comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method according to any one of claims 1 to 5.

8. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images