Low-power-consumption voice recognition method and device of photovoltaic camera

Abstract

The invention relates to the field of voice recognition control, and discloses a low-power-consumption voice recognition method and device for a photovoltaic camera, and the method comprises the steps: determining the first recognition information of a target voice through a first recognition unit, and obtaining the real-time photovoltaic power supply power of the photovoltaic camera when the first recognition information meets a preset first recognition condition; when the real-time photovoltaic power supply power is greater than the preset real-time photovoltaic power supply power, waking up a second recognition unit to recognize subsequent voice of the target voice; and when the real-time photovoltaic power supply power is smaller than or equal to the preset real-time photovoltaic power supply power, waking up the third recognition unit to recognize the subsequent voice of the target voice. And when the real-time photovoltaic power supply power is smaller than or equal to the preset real-time photovoltaic power supply power, acquiring historical photovoltaic power supply power of the photovoltaic camera at multiple moments within the preset first duration from the current moment. The energy consumption can be accurately controlled in combination with the use environment of the photovoltaic camera.

Description

Technical Field

[0001] The present application relates to the field of speech recognition control technology, and more specifically, to a low-power speech recognition method and device for a photovoltaic camera. Background Art

[0002] Photovoltaic cameras are video cameras that integrate photovoltaic power generation technology. Photovoltaic power generation technology provides a continuous power supply for the camera, and photovoltaic power generation technology can continuously convert light energy into electrical energy. Photovoltaic cameras do not require an external power supply and can be deployed in environments that lack a stable power supply. For example, they can be used in outdoor monitoring and remote monitoring. Photovoltaic cameras have a wide range of application prospects. Photovoltaic cameras are increasingly widely used in modern monitoring systems due to their excellent environmental friendliness and low maintenance costs. For solar-powered cameras, it is necessary to reduce the power consumption of video and sound processing in order to increase the battery life of photovoltaic cameras and improve the use effect of photovoltaic cameras.

[0003] Patent CN111755002B (application number: CN202010567523.X) provides a speech recognition device. After the audio memory acquires and stores the original speech signal collected by the microphone and the reference speech signal played by the speaker, the first core determines whether to trigger the first level wake-up state according to the original speech signal and the reference speech signal in a low power consumption state. In the first level wake-up state, the wake-up model is run to trigger the second level wake-up state when the wake-up model recognizes the wake-up according to the original speech signal, and the second core is enabled. In the second level wake-up state, the second core runs the speech recognition model to perform speech recognition on the original speech signal. After acquiring the original speech signal and the reference speech signal, the speech recognition device in patent CN111755002B enables different components step by step to perform speech recognition on the original speech signal, thereby achieving the purpose of reducing energy consumption while maintaining high-performance speech recognition. However, the method in patent CN111755002B cannot accurately control energy consumption under different usage environments. Summary of the invention

[0004] The purpose of this application is to provide a low-power speech recognition method and device for a photovoltaic camera, which solves the technical problem of not being able to accurately control energy consumption in different usage environments, and achieves the technical effect of accurately controlling energy consumption in combination with the usage environment of the photovoltaic camera.

[0005] An embodiment of the present application provides a low-power speech recognition method for a photovoltaic camera, the method comprising: determining first recognition information of a target speech through a first recognition unit, and when the first recognition information meets a preset first recognition condition, obtaining the real-time photovoltaic power supply power of the photovoltaic camera; when the real-time photovoltaic power supply power is greater than the preset real-time photovoltaic power supply power, waking up the second recognition unit to recognize the subsequent speech of the target speech; when the real-time photovoltaic power supply power is less than or equal to the preset real-time photovoltaic power supply power, waking up the third recognition unit to recognize the subsequent speech of the target speech; wherein the power consumption of the second recognition unit is greater than the power consumption of the third recognition unit.

[0006] In a possible implementation, the method also includes: when the real-time photovoltaic power supply power is less than or equal to the preset real-time photovoltaic power supply power, obtaining the historical photovoltaic power supply power of the photovoltaic camera at multiple moments within a preset first time period from the current moment; when the historical photovoltaic power supply power at multiple moments within the preset first time period meets the preset photovoltaic power supply power condition, recognizing the subsequent voice of the target voice through the second recognition unit, and the third recognition unit is turned off when the second recognition unit recognizes the subsequent voice of the target voice; wherein the preset photovoltaic power supply power condition includes that a preset number of historical photovoltaic power supply powers within the preset first time period are greater than a preset first photovoltaic power supply threshold; or the average power of the historical photovoltaic power supply powers at multiple moments within the preset first time period is greater than a preset second photovoltaic power supply threshold; or the historical photovoltaic power supply powers at multiple moments within the preset first time period gradually increase in time sequence, and the maximum historical photovoltaic power supply power among the historical photovoltaic power supply powers at multiple moments within the preset first time period is greater than a preset third photovoltaic power supply threshold.

[0007] In another possible implementation, when the historical photovoltaic power supply power at multiple moments within a preset first time length meets the preset photovoltaic power supply power condition, the subsequent voice of the target voice is recognized by the second recognition unit, including: obtaining the historical photovoltaic power supply power of the photovoltaic camera at multiple moments within a preset second time length from the current moment; wherein the preset second time length is less than the preset first time length; when the historical photovoltaic power supply power at multiple moments within the preset second time length is greater than or equal to a preset fourth photovoltaic power supply threshold, the subsequent voice of the target voice is recognized by the second recognition unit; when the historical photovoltaic power supply power at multiple moments within the preset second time length is less than the preset fourth photovoltaic power supply threshold, the subsequent voice of the target voice is recognized by the third recognition unit, and the second recognition unit is turned off when the third recognition unit recognizes the subsequent voice of the target voice.

[0008] In another possible implementation, the method also includes: when the real-time photovoltaic power supply power is less than or equal to the preset real-time photovoltaic power supply power, obtaining the remaining power value of the photovoltaic camera; when the remaining power value is greater than the preset power value, waking up the second recognition unit to recognize the subsequent voice of the target voice, and the third recognition unit is turned off when the second recognition unit recognizes the subsequent voice of the target voice.

[0009] In another possible implementation, when the remaining power value is greater than the preset power value, the second recognition unit is awakened to recognize the subsequent voice of the target voice, including: obtaining the maximum volume value of the subsequent voice of the target voice at multiple moments within a preset third time length starting from the current moment; when the maximum volume values ​​at multiple moments within the preset third time length are all greater than the preset volume threshold, the third recognition unit is awakened to recognize the subsequent voice of the target voice, and the second recognition unit is turned off when the third recognition unit recognizes the subsequent voice of the target voice; when the maximum volume values ​​at multiple moments within the preset third time length are all less than or equal to the preset volume threshold or when the maximum volume values ​​at multiple moments within the preset third time length gradually decrease, the second recognition unit is awakened to recognize the subsequent voice of the target voice, and the third recognition unit is turned off when the second recognition unit recognizes the subsequent voice of the target voice.

[0010] In another possible implementation, the method also includes: when the maximum volume values ​​at multiple moments within a preset third time period are all greater than a preset volume threshold, obtaining the noise value in the subsequent speech when the third recognition unit recognizes the subsequent speech of the target speech; when the noise value is greater than the preset noise value, after storing the subsequent speech of the target speech, when the real-time photovoltaic power supply power is greater than the preset real-time photovoltaic power supply power, waking up the second recognition unit to recognize the stored subsequent speech of the target speech.

[0011] An embodiment of the present application also provides a low-power speech recognition device for a photovoltaic camera, comprising a unit for executing any of the methods described above.

[0012] An embodiment of the present application also provides a low-power speech recognition device for a photovoltaic camera, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described above when executing the computer program.

[0013] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the above items is implemented.

[0014] An embodiment of the present application further provides a computer program product, including a computer program, which implements the steps of any of the above methods when executed by a processor.

[0015] An embodiment of the present application also provides a photovoltaic camera, which implements the steps of any of the methods described above when the photovoltaic camera is in operation.

[0016] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0017] The embodiment of the present application provides a low-power speech recognition method for a photovoltaic camera, and the method includes: determining the first recognition information of the target speech through a first recognition unit, and when the first recognition information meets the preset conditions, obtaining the real-time photovoltaic power supply power of the photovoltaic camera; when the real-time photovoltaic power supply power is greater than the preset real-time photovoltaic power supply power, waking up the second recognition unit to recognize the subsequent speech of the target speech; when the real-time photovoltaic power supply power is less than or equal to the preset real-time photovoltaic power supply power, waking up the third recognition unit to recognize the subsequent speech of the target speech; wherein the power consumption of the second recognition unit is greater than the power consumption of the third recognition unit. The low-power speech recognition method for the photovoltaic camera in the embodiment of the present application can perform speech recognition through recognition units with different energy consumption under different photovoltaic power supply conditions, realizes precise control of energy consumption, and improves the endurance of the photovoltaic camera. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1 A schematic flow chart of a low-power speech recognition method for a photovoltaic camera provided in an embodiment of the present application;

[0020] Figure 2 A schematic diagram of the structure of a photovoltaic camera used in a low-power speech recognition method of a photovoltaic camera in an embodiment of the present application;

[0021] Figure 3 This is a schematic diagram of a time range of a preset first duration and a preset second duration in an embodiment of the present application;

[0022] Figure 4 A schematic diagram of the logical structure of a low-power speech recognition device for a photovoltaic camera provided in an embodiment of the present application;

[0023] Figure 5 A schematic diagram of the physical structure of a low-power speech recognition device for a photovoltaic camera provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0025] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0026] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0027] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0028] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0029] After acquiring the original voice signal and the reference voice signal, the voice recognition device in the prior art performs voice recognition on the original voice signal by gradually enabling different components, thereby achieving the purpose of reducing energy consumption while maintaining high-performance voice recognition. However, it is not possible to accurately control energy consumption in different usage environments.

[0030] Based on the above reasons, an embodiment of the present application provides a low-power speech recognition method for a photovoltaic camera, and the method includes: determining the first recognition information of the target speech through a first recognition unit, and when the first recognition information meets the preset conditions, obtaining the real-time photovoltaic power supply power of the photovoltaic camera; when the real-time photovoltaic power supply power is greater than the preset real-time photovoltaic power supply power, waking up the second recognition unit to recognize the subsequent speech of the target speech; when the real-time photovoltaic power supply power is less than or equal to the preset real-time photovoltaic power supply power, waking up the third recognition unit to recognize the subsequent speech of the target speech; wherein the power consumption of the second recognition unit is greater than the power consumption of the third recognition unit. The low-power speech recognition method for the photovoltaic camera in the embodiment of the present application can perform speech recognition through recognition units with different energy consumption under different photovoltaic power supply conditions, realizes precise control of energy consumption, and improves the endurance of the photovoltaic camera.

[0031] In some scenarios, a low-power speech recognition method for a photovoltaic camera according to an embodiment of the present application can be applied to speech recognition control of the photovoltaic camera, which can improve the battery life of the photovoltaic camera.

[0032] The following is a detailed description of a low-power speech recognition method for a photovoltaic camera provided in an embodiment of the present application with reference to specific examples.

[0033] Figure 1 A schematic diagram of a low-power speech recognition method for a photovoltaic camera provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes S110 to S120, and S110 to S120 are described in detail below.

[0034] S110. Determine first recognition information of the target voice through a first recognition unit, and when the first recognition information meets a preset first recognition condition, obtain the real-time photovoltaic power supply power of the photovoltaic camera.

[0035] Figure 2 Schematic diagram of the structure of a photovoltaic camera used in a low-power speech recognition method of a photovoltaic camera in an embodiment of the present application, such as Figure 2 As shown, the photovoltaic camera in the embodiment of the present application includes a photovoltaic solar panel 1 and a camera 2. The camera 2 is provided with a microphone, which can collect sound information and perform voice recognition to realize the intelligent security monitoring function.

[0036] When the low-power speech recognition method of the photovoltaic camera in the embodiment of the present application is working, it can first collect the target speech through the microphone, and perform preliminary recognition of the target speech through the first recognition unit to determine the first recognition information of the target speech. The need for further speech recognition can be determined through the first recognition information.

[0037] During operation, when the first recognition information meets the preset first recognition condition, it means that the target voice needs to be further recognized. At this time, the real-time photovoltaic power supply of the photovoltaic camera can be obtained, and the voice recognition method to be used can be determined based on the real-time photovoltaic power supply.

[0038] Exemplarily, the preset first recognition condition may be determining that the target speech is a human voice, contains keywords, or other determination conditions, and the preset first recognition condition is a determination condition for determining that further recognition of the target speech is required.

[0039] S120. When the real-time photovoltaic power supply power is greater than the preset real-time photovoltaic power supply power, the second recognition unit is awakened to recognize the subsequent speech of the target speech. When the real-time photovoltaic power supply power is less than or equal to the preset real-time photovoltaic power supply power, the third recognition unit is awakened to recognize the subsequent speech of the target speech. The power consumption of the second recognition unit is greater than the power consumption of the third recognition unit.

[0040] After obtaining the real-time photovoltaic power supply power, when the real-time photovoltaic power supply power is greater than the preset real-time photovoltaic power supply power, it means that the photovoltaic power generation power of the photovoltaic camera is large and there is sufficient electricity to supply the photovoltaic camera. At this time, the second recognition unit can be awakened to recognize the subsequent voice of the target voice. The model scale of the second recognition unit is larger and the recognition accuracy is higher, which is suitable for use in high-precision recognition scenarios.

[0041] After obtaining the real-time photovoltaic power supply power, when the real-time photovoltaic power supply power is less than or equal to the preset real-time photovoltaic power supply power, it means that the photovoltaic power generation power of the photovoltaic camera is small and there is not enough real-time photovoltaic power generation power to supply the photovoltaic camera. The third recognition unit can be awakened to recognize the subsequent voice of the target voice. The model scale of the second recognition unit is smaller and the recognition accuracy is average, which is suitable for use in low-energy consumption scenarios.

[0042] It should be noted that the power consumption of the second recognition unit is greater than that of the third recognition unit, so that the target voice can be recognized by the third recognition unit when the power generation power is low, thereby fully reducing the energy consumption of the voice recognition function of the photovoltaic camera.

[0043] It should be noted that the second identification unit and the third identification unit may be respectively arranged in different chips, so as to fully isolate the second identification unit and the third identification unit to achieve power consumption control.

[0044] Exemplarily, the difference between the second recognition unit and the third recognition unit may be that the second recognition unit can extract more keyword information, emotion information, etc., and can play a more powerful role in security monitoring than the third recognition unit.

[0045] The beneficial effect brought about by the above-mentioned implementation method is that voice recognition can be performed through recognition units with different energy consumption under different photovoltaic power supply conditions, thereby achieving precise control of energy consumption and improving the endurance of the photovoltaic camera.

[0046] In some implementations, the above method further includes S210 to S220, and S210 to S220 are described in detail below.

[0047] S210: When the real-time photovoltaic power supply power is less than or equal to the preset real-time photovoltaic power supply power, obtain the historical photovoltaic power supply power of the photovoltaic camera at multiple moments within a preset first time period from the current moment.

[0048] During the use of the photovoltaic camera, when the real-time photovoltaic power supply power is less than or equal to the preset real-time photovoltaic power supply power, it means that the real-time photovoltaic power generation power of the photovoltaic camera is low. However, the photovoltaic camera may temporarily reduce its power generation power due to cloud cover. In order to avoid frequent switching of the voice recognition function of the photovoltaic camera and affect the working effect of the camera, the historical photovoltaic power supply power of the photovoltaic camera at multiple moments within the preset first time period can be obtained, and the working state of the photovoltaic camera can be controlled according to the historical photovoltaic power supply power at multiple moments within the preset first time period.

[0049] Exemplarily, the preset first duration may be 1 hour, 1.5 hours or 2.5 hours.

[0050] Exemplarily, when acquiring the historical photovoltaic power supply powers at multiple moments within a preset first time period, the historical photovoltaic power supply powers at multiple moments may be acquired at equal time intervals within the preset first time period.

[0051] S220. When the historical photovoltaic power supply power at multiple moments within the preset first duration meets the preset photovoltaic power supply power condition, the subsequent voice of the target voice is recognized by the second recognition unit, and the third recognition unit is turned off when the second recognition unit recognizes the subsequent voice of the target voice. The preset photovoltaic power supply power condition includes that a preset number of historical photovoltaic power supply powers within the preset first duration are greater than the preset first photovoltaic power supply threshold. Or the average power of the historical photovoltaic power supply power at multiple moments within the preset first duration is greater than the preset second photovoltaic power supply threshold. Or the historical photovoltaic power supply power at multiple moments within the preset first duration gradually increases in time sequence, and the maximum historical photovoltaic power supply power among the historical photovoltaic power supply powers at multiple moments within the preset first duration is greater than the preset third photovoltaic power supply threshold.

[0052] When the photovoltaic camera is working, when the historical photovoltaic power supply power at multiple moments within the preset first time period meets the preset photovoltaic power supply power condition, it means that the historical photovoltaic power supply power of the photovoltaic camera at multiple moments within the preset first time period meets the predetermined conditions and can reach the expected power. The subsequent voice of the target voice can be recognized by the second recognition unit to improve the voice recognition accuracy; at the same time, the continuous working state of the second recognition unit can be guaranteed to avoid interruptions in the voice recognition quality.

[0053] When the second recognition unit is working, the third recognition unit is turned off when the second recognition unit recognizes the subsequent voice of the target voice, which can further reduce the energy consumption of the photovoltaic camera.

[0054] In some implementations, the preset photovoltaic power supply condition may include a preset number of historical photovoltaic power supply powers within a preset first time period that are greater than a preset first photovoltaic power supply threshold. When a preset number of historical photovoltaic power supply powers within the preset first time period are greater than the preset first photovoltaic power supply threshold, it means that the lighting environment of the photovoltaic camera is better and the photovoltaic power generation power is only temporarily reduced. At this time, the subsequent voice of the target voice can still be recognized by the second recognition unit, thereby ensuring the continuous working state of the second recognition unit.

[0055] Exemplarily, the preset number may be 50% to 80% of the total amount of historical photovoltaic power supply power within the first time period.

[0056] In some implementations, the preset photovoltaic power supply condition may include that the average power of the historical photovoltaic power supply power at multiple moments within a preset first time period is greater than the preset second photovoltaic power supply threshold. When the average power of the historical photovoltaic power supply power at multiple moments within the preset first time period is greater than the preset second photovoltaic power supply threshold, it means that the photovoltaic power generation power of the photovoltaic camera within the preset first time period is large. At this time, voice recognition can still be performed through the second recognition unit, thereby ensuring the continuous working state of the second recognition unit.

[0057] In some implementations, the preset second photovoltaic power supply threshold may be 50% to 60% of the maximum photovoltaic power supply power of the day.

[0058] When designing a photovoltaic camera, the overall working power of the photovoltaic camera is generally adapted to the maximum photovoltaic power supply power of the day under different seasons and weather conditions. By setting the preset second photovoltaic power supply threshold to be based on the maximum photovoltaic power supply power of the day, the working state of the second recognition unit can be controlled with reference to the photovoltaic power supply power of the day, so that the control of the working state of the second recognition unit can adapt to the different influences of light on the day and season, and can ensure that the photovoltaic camera can perform high-precision voice recognition through the second recognition unit, avoid the second recognition unit being in a closed state for a long time, and improve the use effect of the photovoltaic camera.

[0059] In some implementations, the preset photovoltaic power supply condition may include that the historical photovoltaic power supply power at multiple moments within a preset first time period gradually increases in time sequence, and the maximum historical photovoltaic power supply power among the historical photovoltaic power supply power at multiple moments within the preset first time period is greater than a preset third photovoltaic power supply threshold.

[0060] When working, the preset photovoltaic power supply condition may include that the historical photovoltaic power supply power at multiple moments within the preset first time length gradually increases in time sequence. When the historical photovoltaic power supply power at multiple moments within the preset first time length gradually increases in time sequence, it indicates that the historical photovoltaic power supply power at multiple moments within the preset first time length gradually increases and is in a time period of enhanced sunshine, and the reduction in photovoltaic power supply power is only temporarily caused by shading. At the same time, the maximum historical photovoltaic power supply power among the historical photovoltaic power supply power at multiple moments within the preset first time length is greater than the preset third photovoltaic power supply threshold, indicating that the historical photovoltaic power supply power at multiple moments within the preset first time length has reached a relatively large power supply level. At this time, the second identification unit can be started to work, and sufficient power supply can be guaranteed.

[0061] Exemplarily, the preset third photovoltaic power supply threshold may be 60% to 70% of the maximum photovoltaic power supply power of the day, so that the preset third photovoltaic power supply threshold can adapt to the lighting conditions of the photovoltaic camera on that day, thereby improving the use effect of the photovoltaic camera.

[0062] The beneficial effect brought about by the above-mentioned implementation method is that when the cloud movement blocks the camera and causes the power of the camera to change, it can avoid the frequent switching of the voice recognition function of the photovoltaic camera and affect the working effect of the camera.

[0063] The beneficial effect brought about by the above implementation method is that when the photovoltaic power generation power temporarily fluctuates, the continuous working state of the second recognition unit can be guaranteed, thereby avoiding the interruption of the voice recognition quality and ensuring the voice recognition effect.

[0064] In some implementations, when the second recognition unit recognizes the subsequent speech of the target speech, the third recognition unit is turned off after a preset waiting time; when the third recognition unit recognizes the subsequent speech of the target speech, the second recognition unit is turned off after a preset waiting time.

[0065] During operation, when the second recognition unit recognizes the subsequent voice of the target voice, the third recognition unit is turned off after a preset waiting time, so that the third recognition unit can wait for the preset waiting time before turning off, avoiding frequent power on and off of the third recognition unit and affecting the service life of the photovoltaic camera.

[0066] During operation, when the third recognition unit recognizes the subsequent voice of the target voice, the second recognition unit is turned off after a preset waiting time, so that the second recognition unit can wait for the preset waiting time before turning off, avoiding frequent power on and off of the second recognition unit and affecting the service life of the photovoltaic camera.

[0067] The beneficial effect brought about by the above-mentioned implementation method is that when the working state of the second identification unit and the third identification unit is switched, they can be turned off after waiting for a preset period of time, and can delay switching when the photovoltaic power generation conditions change, thereby improving the service life of the photovoltaic camera and avoiding increased energy consumption caused by frequent switching of the second identification unit and the third identification unit.

[0068] In some implementations, in the above-mentioned S220, when the historical photovoltaic power supply power at multiple moments within a preset first time period meets the preset photovoltaic power supply power condition, the subsequent speech of the target speech is recognized by the second recognition unit, including S221 to S222. S221 to S222 are specifically described below.

[0069] S221, obtaining the historical photovoltaic power supply of the photovoltaic camera at multiple moments within a preset second time period from the current moment, wherein the preset second time period is shorter than the preset first time period.

[0070] Figure 3 Schematic diagram of a time range of a preset first duration and a preset second duration in an embodiment of the present application, such as Figure 3 As shown, when working, when the historical photovoltaic power supply power at multiple moments within a preset first time period meets the preset photovoltaic power supply power condition, it means that the photovoltaic power supply power within the preset first time period from the current moment meets the requirement. In order to judge the photovoltaic power supply effect more accurately, the historical photovoltaic power supply power of the photovoltaic camera at multiple moments within a preset second time period from the current moment can be obtained. The preset second time period is less than the preset first time period. Then, the photovoltaic power supply situation can be more accurately judged through the historical photovoltaic power supply power at multiple moments within the preset second time period from the current moment.

[0071] Exemplarily, the preset second duration may be 20% to 30% of the preset first duration.

[0072] Exemplarily, when acquiring the historical photovoltaic power supply powers at multiple moments within the preset second time period, the historical photovoltaic power supply powers at multiple moments within the preset second time period may be acquired at equal time intervals.

[0073] S222: When the historical photovoltaic power supply powers at multiple moments within the preset second time period are all greater than or equal to the preset fourth photovoltaic power supply threshold, the subsequent voice of the target voice is recognized by the second recognition unit. When the historical photovoltaic power supply powers at multiple moments within the preset second time period are all less than the preset fourth photovoltaic power supply threshold, the subsequent voice of the target voice is recognized by the third recognition unit, and the second recognition unit is turned off when the third recognition unit recognizes the subsequent voice of the target voice.

[0074] During operation, when the historical photovoltaic power supply powers at multiple moments within the preset second time period are greater than or equal to the preset fourth photovoltaic power supply threshold, it means that the historical photovoltaic power supply powers at multiple moments within the preset second time period are large. At this time, the subsequent voice of the target voice can be recognized by the second recognition unit to ensure the accuracy of voice recognition.

[0075] Exemplarily, the preset fourth photovoltaic power supply threshold may be 40% to 50% of the maximum photovoltaic power supply power of the day.

[0076] Exemplarily, the preset fourth photovoltaic power supply threshold can be lower than the preset third photovoltaic power supply threshold, so that the photovoltaic power supply threshold within the preset second time period closer to the current moment is lower, and voice recognition can be performed through the third recognition unit when the photovoltaic power supply power in the local time period is low, thereby avoiding the situation where the photovoltaic power supply power within the preset second time period closer to the current moment is low and the third recognition unit with lower power consumption is used to perform voice recognition, thereby avoiding the situation where the photovoltaic camera's energy consumption is too high and the photovoltaic power supply power is low, affecting the battery life.

[0077] During operation, when the historical photovoltaic power supply powers at multiple moments within the preset second time period are all less than the preset fourth photovoltaic power supply threshold, it means that the photovoltaic power supply power within the preset second time period is low. At this time, the subsequent voice of the target voice can be recognized by the third recognition unit to reduce energy consumption during voice recognition.

[0078] When the third recognition unit recognizes the subsequent speech of the target speech, the second recognition unit is turned off to reduce the energy consumption of the photovoltaic camera.

[0079] The beneficial effect brought about by the above-mentioned implementation method is that when the working state of the photovoltaic camera is controlled by the photovoltaic power supply power within a preset first time period, the voice recognition function is further controlled by the photovoltaic power supply power within a preset second time period closer to the current moment, thereby improving the accuracy of energy consumption control of voice recognition and improving the battery life of the photovoltaic camera.

[0080] The beneficial effect brought about by the above-mentioned implementation method is that the preset fourth photovoltaic power supply threshold is lower than the preset third photovoltaic power supply threshold, and voice recognition can be performed through the third recognition unit when the photovoltaic power supply power is low in a local time period, thereby avoiding the situation where the photovoltaic power supply power is low in a preset second time period closer to the current moment and performing voice recognition through the third recognition unit with lower power consumption, thereby avoiding the situation where the photovoltaic camera's energy consumption is too high and the photovoltaic power supply power is low, affecting the battery life.

[0081] In some implementations, the above method further includes S310 to S320, and S310 to S320 are described in detail below.

[0082] S310: When the real-time photovoltaic power supply power is less than or equal to the preset real-time photovoltaic power supply power, obtain the remaining power value of the photovoltaic camera.

[0083] During work, the voice recognition function can also be controlled by the remaining power value of the photovoltaic camera. When the real-time photovoltaic power supply is less than or equal to the preset real-time photovoltaic power supply, it means that the photovoltaic power supply is small. At this time, the remaining power value of the photovoltaic camera can be obtained, and the voice recognition function can be controlled according to the remaining power value of the photovoltaic camera.

[0084] S320: When the remaining power value is greater than the preset power value, the second recognition unit is awakened to recognize the subsequent voice of the target voice, and the third recognition unit is turned off when the second recognition unit recognizes the subsequent voice of the target voice.

[0085] After obtaining the remaining power value of the photovoltaic camera, when the remaining power value is greater than the preset power value, it means that the remaining power of the photovoltaic camera is large. At this time, the second recognition unit can be awakened to recognize the subsequent voice of the target voice. High-precision voice recognition is achieved through the second recognition unit. When the second recognition unit recognizes the subsequent voice of the target voice, the third recognition unit is turned off.

[0086] Exemplarily, the preset power value may be 50% to 60% of the rated power value of the photovoltaic camera.

[0087] The beneficial effect brought about by the above-mentioned implementation method is that the voice recognition function can be controlled according to the remaining power value of the photovoltaic camera, so that high-precision voice recognition can be achieved when the remaining power of the photovoltaic camera is high, thereby improving the use effect of the photovoltaic camera.

[0088] In some implementations, in the above S320, when the remaining power value is greater than the preset power value, the second recognition unit is awakened to recognize the subsequent voice of the target voice, including S321 to S322, and S321 to S322 are specifically described below.

[0089] S321. Obtain the maximum volume values ​​of the subsequent speech of the target speech at multiple moments within a preset third time duration starting from the current moment.

[0090] When waking up the second recognition unit to recognize the subsequent voice of the target voice, due to the large energy consumption of the second recognition unit, the expected working time of the second recognition unit can be predicted, and the voice recognition function of the photovoltaic camera can be controlled according to the expected working time of the second recognition unit to ensure the continuity of the recognition unit used in the voice recognition and avoid failures in the voice recognition process.

[0091] During operation, in order to predict the expected working time of the second recognition unit, the maximum volume values ​​of the subsequent speech of the target speech at multiple moments within a preset third time period can be obtained, and the expected working time of the second recognition unit can be predicted based on the maximum volume values.

[0092] Exemplarily, the preset third duration may be 1 minute, 3 minutes or 5 minutes.

[0093] S322: When the maximum volume values ​​at multiple moments within the preset third duration are all greater than the preset volume threshold, the third recognition unit is awakened to recognize the subsequent voice of the target voice, and the second recognition unit is turned off when the third recognition unit recognizes the subsequent voice of the target voice. When the maximum volume values ​​at multiple moments within the preset third duration are all less than or equal to the preset volume threshold or when the maximum volume values ​​at multiple moments within the preset third duration gradually decrease, the second recognition unit is awakened to recognize the subsequent voice of the target voice, and the third recognition unit is turned off when the second recognition unit recognizes the subsequent voice of the target voice.

[0094] After obtaining the maximum volume values ​​of multiple moments within the preset third time length, when the maximum volume values ​​of multiple moments within the preset third time length are all greater than the preset volume threshold, the maximum volume values ​​of multiple moments within the preset third time length are all large, indicating that the subsequent voice of the target voice may continue for a long time. At this time, in order to reduce the energy consumption of voice recognition, the third recognition unit can be awakened to recognize the subsequent voice of the target voice to ensure that voice recognition can continue for a long time. The second recognition unit can be turned off when the third recognition unit recognizes the subsequent voice of the target voice.

[0095] After obtaining the maximum volume values ​​of multiple moments within the preset third duration, when the maximum volume values ​​of multiple moments within the preset third duration are all less than or equal to the preset volume threshold or when the maximum volume values ​​of multiple moments within the preset third duration gradually decrease, it indicates that the target voice is gradually decreasing or the preset volume threshold is small and the recognition demand is low, indicating that the recognition time of the target voice may be short, and the second recognition unit can be awakened to recognize the subsequent voice of the target voice, so as to avoid switching the recognition unit used for voice recognition during the voice recognition process, ensure the continuity of voice recognition, and avoid voice recognition errors. At the same time, the third recognition unit is turned off when the second recognition unit recognizes the subsequent voice of the target voice.

[0096] The beneficial effect brought about by the above-mentioned implementation method is that the voice recognition function of the photovoltaic camera can be controlled according to the expected working time of the second recognition unit, thereby ensuring the continuity of the recognition unit used in the voice recognition and avoiding failures in the voice recognition process.

[0097] The beneficial effect brought about by the above-mentioned implementation method is that when the remaining power value is greater than the preset power value, when the second recognition unit is awakened to recognize the subsequent voice of the target voice, when the subsequent voice of the target voice may last for a long time, the energy consumption of voice recognition can be reduced by awakening the third recognition unit to recognize the subsequent voice of the target voice.

[0098] The beneficial effect brought about by the above-mentioned implementation method is that when the remaining power value is greater than the preset power value, when the second recognition unit is awakened to recognize the subsequent voice of the target voice, when the recognition time of the target voice may be short, the second recognition unit is awakened to recognize the subsequent voice of the target voice, thereby avoiding switching the recognition unit used for voice recognition during the voice recognition process.

[0099] In some implementations, the above method further includes S410 to S420, and S410 to S420 are described in detail below.

[0100] S410. When the maximum volume values ​​at multiple moments within the preset third time period are all greater than the preset volume threshold, obtain the noise value in the subsequent speech when the third recognition unit recognizes the subsequent speech of the target speech.

[0101] During operation, when the maximum volume values ​​at multiple moments within a preset third time period are all greater than the preset volume threshold, the third recognition unit can be awakened to recognize the subsequent voice of the target voice. Since the recognition accuracy of the third recognition unit is low, measures can be taken to supplement the recognition effect of the third recognition unit.

[0102] When supplementing the recognition effect of the third recognition unit, the noise value in the subsequent speech when the third recognition unit recognizes the subsequent speech of the target speech can be obtained, and the noise value in the subsequent speech represents the effect of the recognition by the third recognition unit.

[0103] Exemplarily, the noise value in the subsequent speech can be judged by the voiceprint features. Since speech recognition involves more computational complexity and data processing requirements, the hardware energy consumption of speech recognition is usually higher than that of voiceprint feature extraction, which makes the energy consumption of voiceprint feature judgment lower and facilitates the judgment of the noise value.

[0104] S420. When the noise value is greater than the preset noise value, after storing the subsequent speech of the target speech, when the real-time photovoltaic power supply power is greater than the preset real-time photovoltaic power supply power, waking up the second recognition unit to recognize the subsequent speech of the stored target speech.

[0105] When the noise value is greater than the preset noise value, it means that there is a lot of noise in the subsequent speech of the target speech, and the recognition effect of the third recognition unit may not be good. At this time, the subsequent speech of the target speech can be stored. When the real-time photovoltaic power supply power is greater than the preset real-time photovoltaic power supply power, the second recognition unit is awakened to recognize the subsequent speech of the stored target speech. The recognition effect of the speech with a larger noise value is guaranteed by the second recognition unit.

[0106] The beneficial effect brought about by the above implementation method is that when there is a lot of noise in the subsequent speech of the target speech, the recognition effect of the third recognition unit may not be good, and the recognition effect of the speech with a large noise value can be guaranteed by the second recognition unit.

[0107] An embodiment of the present application also provides a low-power speech recognition device for a photovoltaic camera, comprising a unit for executing any of the methods described above.

[0108] Figure 4 A schematic diagram of the logical structure of a low-power speech recognition device for a photovoltaic camera provided in one embodiment of the present application is shown in FIG. Figure 4 As shown, the device 3 of this embodiment includes a processing unit 31, a storage unit 32 and a transceiver unit 33. The processing unit 31 is used to process data, the storage unit 32 is used to store data, and the transceiver unit 33 is used to send and receive data. The processing unit 31, the storage unit 32 and the transceiver unit 33 cooperate with each other to implement the above method. The beneficial effects brought by the embodiment of the present application have been described in the above method and will not be repeated here.

[0109] An embodiment of the present application also provides a low-power speech recognition device for a photovoltaic camera, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described above when executing the computer program.

[0110] Figure 5 A schematic diagram of the physical structure of a low-power speech recognition device for a photovoltaic camera provided in one embodiment of the present application, such as Figure 5 As shown, the device 4 of this embodiment includes: at least one processor 40 ( Figure 5 Only one processor 40 is shown in the figure), a memory 41, and a computer program 42 stored in the memory 41 and executable on the at least one processor 40, and the processor 40 implements the steps in any of the above-mentioned method embodiments when executing the computer program 42. The beneficial effects brought about by the embodiments of the present application have been described in the above-mentioned methods and will not be repeated here.

[0111] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0112] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0113] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0114] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0115] The embodiment of the present application also provides a photovoltaic camera, which can implement the steps of any of the methods described above when working.

[0116] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0117] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0118] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0119] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0120] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A low-power speech recognition method for a photovoltaic camera, characterized in that: The method comprises: Determine first recognition information of the target voice by a first recognition unit, and when the first recognition information meets a preset first recognition condition, obtain the real-time photovoltaic power supply power of the photovoltaic camera; When the real-time photovoltaic power supply power is greater than the preset real-time photovoltaic power supply power, the second recognition unit is awakened to recognize the subsequent voice of the target voice; when the real-time photovoltaic power supply power is less than or equal to the preset real-time photovoltaic power supply power, the third recognition unit is awakened to recognize the subsequent voice of the target voice; wherein the power consumption of the second recognition unit is greater than the power consumption of the third recognition unit.

2. The method according to claim 1, characterized in that The method further comprises: When the real-time photovoltaic power supply power is less than or equal to the preset real-time photovoltaic power supply power, obtaining the historical photovoltaic power supply power of the photovoltaic camera at multiple moments within a preset first time period from the current moment; When the historical photovoltaic power supply power at multiple moments within the preset first time period meets the preset photovoltaic power supply power condition, the subsequent speech of the target speech is recognized by the second recognition unit, and the third recognition unit is turned off when the second recognition unit recognizes the subsequent speech of the target speech; Among them, the preset photovoltaic power supply power condition includes that a preset number of historical photovoltaic power supply powers within a preset first time period are greater than a preset first photovoltaic power supply threshold; or the average power of the historical photovoltaic power supply powers at multiple moments within the preset first time period is greater than a preset second photovoltaic power supply threshold; or the historical photovoltaic power supply powers at multiple moments within the preset first time period gradually increase in time sequence, and the maximum historical photovoltaic power supply power among the historical photovoltaic power supply powers at multiple moments within the preset first time period is greater than a preset third photovoltaic power supply threshold.

3. The method according to claim 2, characterized in that When the historical photovoltaic power supply powers at multiple moments within the preset first time period meet the preset photovoltaic power supply power condition, the subsequent speech of the target speech is recognized by the second recognition unit, including: Obtain the historical photovoltaic power supply power of the photovoltaic camera at multiple moments within a preset second time period from the current moment; wherein the preset second time period is less than the preset first time period; When the historical photovoltaic power supply powers at multiple moments within the preset second time length are greater than or equal to the preset fourth photovoltaic power supply threshold, the subsequent voice of the target voice is recognized by the second recognition unit; when the historical photovoltaic power supply powers at multiple moments within the preset second time length are less than the preset fourth photovoltaic power supply threshold, the subsequent voice of the target voice is recognized by the third recognition unit, and the second recognition unit is turned off when the third recognition unit recognizes the subsequent voice of the target voice.

4. The method according to claim 3, characterized in that The method further comprises: When the real-time photovoltaic power supply power is less than or equal to the preset real-time photovoltaic power supply power, the remaining power value of the photovoltaic camera is obtained; When the remaining power value is greater than the preset power value, the second recognition unit is awakened to recognize the subsequent voice of the target voice, and the third recognition unit is turned off when the second recognition unit recognizes the subsequent voice of the target voice.

5. The method according to claim 4, characterized in that When the remaining power value is greater than the preset power value, waking up the second recognition unit to recognize the subsequent voice of the target voice, including: Obtaining the maximum volume values ​​of subsequent voices of the target voice at multiple times within a preset third time period starting from the current time; When the maximum volume values ​​of multiple moments within the preset third time length are all greater than the preset volume threshold, the third recognition unit is awakened to recognize the subsequent voice of the target voice, and the second recognition unit is turned off when the third recognition unit recognizes the subsequent voice of the target voice; when the maximum volume values ​​of multiple moments within the preset third time length are all less than or equal to the preset volume threshold or when the maximum volume values ​​of multiple moments within the preset third time length gradually decrease, the second recognition unit is awakened to recognize the subsequent voice of the target voice, and the third recognition unit is turned off when the second recognition unit recognizes the subsequent voice of the target voice.

6. The method according to claim 5, characterized in that The method further comprises: When the maximum volume values ​​at multiple moments within the preset third time period are all greater than the preset volume threshold, obtaining the noise value in the subsequent speech when the third recognition unit recognizes the subsequent speech of the target speech; When the noise value is greater than the preset noise value, the subsequent speech of the target speech is stored, and when the real-time photovoltaic power supply power is greater than the preset real-time photovoltaic power supply power, the second recognition unit is awakened to recognize the subsequent speech of the stored target speech.

7. A low-power speech recognition device for a photovoltaic camera, characterized in that: Comprising means for performing the method according to any one of claims 1 to 6.

8. A low-power speech recognition device for a photovoltaic camera, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A photovoltaic camera, characterized in that: When the photovoltaic camera is in operation, the steps of the method described in any one of claims 1 to 6 can be implemented.

Images