Charger control method and device based on voice recognition, equipment and medium

Abstract

The invention relates to the technical field of charger control. In particular to a charger control method, device, equipment and medium based on voice recognition, and the method comprises the steps: comparing standby duration information with a preset standby duration threshold value, if the standby duration information is greater than the preset standby duration threshold value, selecting initial charging curve parameter information to adjust the output power of a charger, and if the initial charging curve parameter information is greater than the preset standby duration threshold value, adjusting the output power of the charger. If the standby duration information is smaller than a preset standby duration threshold value, obtaining user voice instruction information, processing the voice instruction information through an offline voice recognition model to obtain a voice recognition result, comparing the voice recognition result with a preset voice instruction library, and if the voice recognition result and the preset voice instruction library are successfully recognized, sending the voice recognition result to the user. If yes, recognition success prompt information is generated, a target charging curve selected by the user is confirmed according to the recognition success prompt information, and target charging curve parameter information is obtained based on the target charging curve. The device has the effect of improving the working efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of charger control, and in particular to a charger control method, device, equipment and medium based on voice recognition. Background Art

[0002] In the prior art, chargers with a single charging curve cannot meet the needs of multiple batteries, and although chargers with multiple charging curves are more powerful, they require operators to frequently manually switch charging curves, resulting in inconvenience. In particular, when multiple batteries need to be used at the same time, operators need to constantly switch, which reduces work efficiency to a certain extent. Summary of the invention

[0003] In order to improve work efficiency, the present application provides a charger control method, device, equipment and medium based on voice recognition.

[0004] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A charger control method based on voice recognition, the charger control method based on voice recognition comprising: Get the charger's standby time information; Comparing the standby time information with a preset standby time threshold, and if the standby time information is greater than the preset standby time threshold, selecting initial charging curve parameter information to adjust the output power of the charger; If the standby time information is less than the preset standby time threshold, obtaining user voice command information; Processing the voice command information through an offline voice recognition model to obtain a voice recognition result; Comparing the speech recognition result with a preset speech instruction library, and generating a recognition success prompt message if the speech recognition result and the preset speech instruction library are successfully recognized; According to the recognition success prompt information, confirm the target charging curve selected by the user, and obtain target charging curve parameter information based on the target charging curve; Based on the charging curve parameter information, the charging power of the charger is adjusted to adapt to the current charging state.

[0005] By adopting the above technical solution, by obtaining the standby time information of the charger and comparing it with the preset standby time threshold, the charger can automatically determine whether the output power needs to be adjusted, avoiding manual intervention and unnecessary waiting time. If the standby time exceeds the threshold, the appropriate charging curve will be automatically selected and the power will be adjusted to quickly start the charging operation, thereby reducing the power adjustment lag caused by long standby. If the standby time does not reach the preset threshold, the solution uses voice commands to control the selection of the charging curve. The user does not need manual operation and can quickly switch the charging mode through voice commands, which greatly improves the efficiency of charging curve selection. In addition, through offline voice recognition technology, the charger can quickly recognize user voice commands and match them with the command library without the need for Internet connection. Even in a busy environment, users can complete the switching of charging curves through concise and clear voice commands, avoiding the cumbersome operation and time waste caused by traditional physical buttons, remote controls or mobile phone APP operations. For each voice command, the target charging curve will be automatically confirmed after successful recognition, and the charging parameters will be adjusted according to the target curve, so that the charging process can quickly and accurately adapt to the current charging needs, avoiding charging delays caused by manual selection and improper operation.

[0006] In a preferred example, the present application may be further configured as follows: the initial charging curve parameter information includes: Obtaining charging status parameter information of the charger; Determine an initial charging curve according to the charging state parameter information and in combination with a charging curve selection rule; Based on the initial charging curve, charging curve parameter information corresponding to the initial charging curve is acquired from a charging curve library to obtain the initial charging curve parameter information.

[0007] By adopting the above technical solution, by obtaining the charging status parameter information of the charger, the operating status of the charging device can be grasped in real time, including key data such as battery power, charging progress, temperature, etc., to ensure dynamic monitoring of the charging process. Then, combining the charging status parameter information and the preset charging curve selection rules, the initial charging curve can be intelligently determined, avoiding selection errors and delays caused by human intervention, and ensuring accurate adaptation of the charging mode.

[0008] In a preferred example, the present application may be further configured as follows: determining the initial charging curve according to the charging state parameter information in combination with the charging curve selection rule includes: The charging curve selection rule obtains the initial charging curve based on the following formula: Wherein, C is the selected initial charging curve, and C iis the i-th candidate charging curve in the charging curve library, T is the current battery temperature, and T Ci is the optimal temperature range of the i-th charging curve, H is the current battery health information, and H Ci is the matching health state of the i-th charging curve, L is the current load state, and L Ci is the optimal load matching value of the i-th charging curve, V is the current battery voltage, and V Ci is the target voltage of the i-th charging curve, α1 is the weight coefficient of T, α2 is the weight coefficient of H, α3 is the weight coefficient of L, and α4 is the weight coefficient of V.

[0009] By adopting the above technical solution, the most suitable initial charging curve is calculated by comprehensively considering multiple factors such as battery temperature, battery health status, load status and battery voltage. Specifically, the selection of the charging curve is through the weighted calculation of each factor in the formula to ensure that each charging link can be optimally matched according to the current battery and charging environment. Through this refined weighted algorithm, it can ensure that the charging process is adaptively adjusted under different conditions, avoiding overcharging or undercharging problems caused by mismatching charging curves.

[0010] In a preferred example, the present application may be further configured as follows: the voice command information is processed by an offline voice recognition model to obtain a voice recognition result, including: The offline speech recognition model is used to perform speech feature extraction and acoustic decoding on the speech instruction information to obtain the speech recognition result.

[0011] By adopting the above technical solution, the dependence on traditional physical buttons, remote controls or APPs can be significantly reduced, making the operation of the device simpler and faster. Users can select charging curves or perform other operations simply by voice, thereby improving the efficiency of the charging process and user experience, especially in situations where it is inconvenient to operate with hands or in an environment that is inconvenient to access, and can truly achieve convenient operation with both hands freed.

[0012] In a preferred example, the present application can be further configured as follows: comparing the speech recognition result with a preset speech instruction library, and if the speech recognition result is successfully recognized by the preset speech instruction library, generating a recognition success prompt message, including: Calculating the similarity between the speech recognition result and the instructions in the preset speech instruction library to obtain an instruction similarity result; If the instruction similarity result exceeds the instruction matching threshold, it is confirmed that the speech recognition result successfully matches the instruction in the preset voice instruction library, and the recognition success prompt information is generated.

[0013] By adopting the above technical solution, when the similarity between the voice command and the command in the preset command library exceeds the matching threshold, the successful recognition of the command is promptly confirmed, and a prompt message of successful recognition is generated, thereby ensuring the accurate execution of the user's operation. By calculating the similarity between the voice recognition results and the commands in the command library, it is possible to effectively deal with differences in voice input, such as pronunciation deviations or background noise, and reduce operational errors caused by misrecognition. At the same time, it is possible to automatically filter out unmatched commands according to the preset matching threshold, thereby avoiding misoperation.

[0014] In a preferred example, the present application may be further configured as follows: if the instruction similarity result exceeds the instruction matching threshold, then confirming that the speech recognition result successfully matches the instruction in the preset voice instruction library, generating the recognition success prompt information, and further comprising: If the instruction similarity result does not exceed the instruction matching threshold, a recognition failure prompt message is generated.

[0015] By adopting the above technical solution, when the similarity between the voice command and the command in the preset command library does not reach the set matching threshold, a recognition failure prompt message is generated in time, thereby prompting the user that the voice command has not been successfully recognized. This mechanism can ensure that invalid or inaccurate commands are not mistakenly executed, avoiding operational errors caused by misrecognition. At the same time, by generating a failure prompt message, the user can quickly realize the problem and reissue the correct command.

[0016] In a preferred example, the present application may be further configured as follows: obtaining target charging curve parameter information based on the target charging curve includes: Based on the target charging curve, charging curve parameter information corresponding to the target charging curve is acquired from the charging curve library to obtain the target charging curve parameter information.

[0017] By adopting the above technical solution, during the charging process, the charging curve parameter information matching the target charging curve is automatically obtained from the charging curve library, avoiding the time waste of manual adjustment and selection. This automated process speeds up the response speed of the charging operation, reduces the need for human intervention, and enables the device to enter the optimal charging state in the shortest time.

[0018] The second object of the invention is achieved by the following technical solutions: A charger control device based on voice recognition, the charger control device based on voice recognition comprising: A module for obtaining information about the standby time of a charger is used to obtain information about the standby time of a charger; A standby time comparison and charging curve selection module, used to compare the standby time information with a preset standby time threshold, and if the standby time information is greater than the preset standby time threshold, select the initial charging curve parameter information to adjust the output power of the charger; A voice command acquisition module, configured to acquire user voice command information if the standby time information is less than the preset standby time threshold; An offline speech recognition processing module is used to process the speech instruction information through an offline speech recognition model to obtain a speech recognition result; A voice recognition result and instruction library comparison module is used to compare the voice recognition result with a preset voice instruction library, and if the voice recognition result and the preset voice instruction library are successfully recognized, a recognition success prompt message is generated; A target charging curve confirmation and parameter acquisition module, used to confirm the target charging curve selected by the user according to the recognition success prompt information, and obtain the target charging curve parameter information based on the target charging curve; The charging power adjustment module is used to adjust the charging power of the charger based on the charging curve parameter information to adapt to the current charging state.

[0019] By adopting the above technical solution, by obtaining the standby time information of the charger and comparing it with the preset standby time threshold, the charger can automatically determine whether the output power needs to be adjusted, avoiding manual intervention and unnecessary waiting time. If the standby time exceeds the threshold, the appropriate charging curve will be automatically selected and the power will be adjusted to quickly start the charging operation, thereby reducing the power adjustment lag caused by long standby. If the standby time does not reach the preset threshold, the solution uses voice commands to control the selection of the charging curve. The user does not need manual operation and can quickly switch the charging mode through voice commands, which greatly improves the efficiency of charging curve selection. In addition, through offline voice recognition technology, the charger can quickly recognize user voice commands and match them with the command library without the need for Internet connection. Even in a busy environment, users can complete the switching of charging curves through concise and clear voice commands, avoiding the cumbersome operation and time waste caused by traditional physical buttons, remote controls or mobile phone APP operations. For each voice command, the target charging curve will be automatically confirmed after successful recognition, and the charging parameters will be adjusted according to the target curve, so that the charging process can quickly and accurately adapt to the current charging needs, avoiding charging delays caused by manual selection and improper operation.

[0020] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned voice recognition charger control method when executing the computer program.

[0021] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the charger control method based on voice recognition are implemented.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: 1. By obtaining the standby time information of the charger and comparing it with the preset standby time threshold, the charger can automatically determine whether the output power needs to be adjusted, avoiding manual intervention and unnecessary waiting time. If the standby time exceeds the threshold, the appropriate charging curve will be automatically selected and the power will be adjusted to quickly start the charging operation, thereby reducing the power adjustment lag caused by long standby time. If the standby time does not reach the preset threshold, the solution uses voice commands to control the selection of the charging curve. Users do not need manual operation and can quickly switch the charging mode through voice commands, which greatly improves the efficiency of charging curve selection. In addition, through offline voice recognition technology, the charger can quickly recognize user voice commands and match them with the command library without the need for an Internet connection. Even in a busy environment, users can complete the switching of charging curves through concise and clear voice commands, avoiding the cumbersome operations and time waste caused by traditional physical buttons, remote controls or mobile phone APP operations. For each voice command, the target charging curve will be automatically confirmed after successful recognition, and the charging parameters will be adjusted according to the target curve, so that the charging process can quickly and accurately adapt to the current charging needs, avoiding charging delays caused by manual selection and improper operation; 2. It can significantly reduce the reliance on traditional physical buttons, remote controls or apps, making the operation of the device easier and faster. Users can select the charging curve or perform other operations simply by voice, thereby improving the efficiency of the charging process and user experience, especially when the hands are inconvenient to operate or the environment is inconvenient to contact, it can truly realize the convenient operation of freeing both hands; 3. When the similarity between the voice command and the commands in the preset command library does not reach the set matching threshold, a recognition failure prompt message is generated in time to prompt the user that the voice command has not been successfully recognized. This mechanism can ensure that invalid or inaccurate commands are not mistakenly executed, avoiding operational errors caused by misrecognition. At the same time, by generating a failure prompt message, the user can quickly realize the problem and re-issue the correct command. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of a charger control method using voice recognition in one embodiment of the present application; Figure 2 This is a flowchart for implementing step S20 in the charger control method of voice recognition in one embodiment of the present application; Figure 3 It is a flowchart for implementing step S202 in the charger control method of voice recognition in one embodiment of the present application; Figure 4 It is a flowchart for implementing step S40 in the charger control method of voice recognition in one embodiment of the present application; Figure 5 This is a flowchart for implementing step S50 in the charger control method of voice recognition in one embodiment of the present application; Figure 6 It is a flowchart for implementing step S502 in the charger control method of voice recognition in one embodiment of the present application; Figure 7 This is a flowchart of the implementation after step S60 in the charger control method of voice recognition in one embodiment of the present application; Figure 8 It is a principle block diagram of a charger control device for voice recognition in one embodiment of the present application; Fig. 9 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application is further described in detail below in conjunction with the accompanying drawings.

[0025] In one embodiment, if Figure 1 As shown, the present application discloses a charger control method based on voice recognition, which specifically includes the following steps: S10: Obtaining the standby time information of the charger.

[0026] Specifically, the charger will record the current standby time through an internal timer or sensor. When the charger is in standby mode, the standby time information is updated in real time, and subsequent comparison and judgment are performed. The standby time information is the cumulative time that the charger has not performed any operation since the last charge or power-on. It is usually counted in minutes and stored in the charger's memory. S20: Compare the standby time information with a preset standby time threshold, and if the standby time information is greater than the preset standby time threshold, select the initial charging curve parameter information to adjust the output power of the charger.

[0027] Specifically, the standby time information is compared with a preset threshold. If the standby time exceeds the preset value, the process of automatically selecting the charging curve is triggered. In this case, the charger selects a default initial charging curve based on the current battery characteristics, load requirements and environmental conditions. The parameters of the charging curve include current, voltage and other information. At the same time, the charger main control MCU will adjust the charging power according to the parameters to ensure the efficiency and safety of the charging process.

[0028] S30: If the standby time information is less than a preset standby time threshold, obtaining user voice command information.

[0029] Specifically, when the standby time is less than the preset value, the charger receives voice commands from the user. The user can control the selection of the charging curve through voice commands. At this time, the charger will turn on the microphone to capture the user's voice commands, such as selecting curve 1 or adjusting the output current, and perform subsequent processing after recognition.

[0030] S40: Processing the voice command information through an offline voice recognition model to obtain a voice recognition result.

[0031] Specifically, by calling Hailingke's HLK_V20 offline speech recognition module, the received voice signal is converted into a digital signal and transmitted to the module for processing. The HLK_V20 offline speech recognition module analyzes the voice information through a pre-loaded speech recognition model, compares the voice command information with the commands in the built-in command library, and finally outputs the speech recognition result, which includes the matching degree of the command and the corresponding command identification.

[0032] Furthermore, the HLK_V20 module supports offline recognition of 150 local commands, and can select different charging curves according to the user's voice commands. The HLK_V20 offline voice recognition module can also automatically optimize according to the clarity of the voice input and background noise to improve recognition accuracy.

[0033] S50: Compare the speech recognition result with the preset speech instruction library. If the speech recognition result is successfully recognized by the preset speech instruction library, a recognition success prompt message is generated.

[0034] Specifically, by calculating the similarity with the built-in voice command library, the matching degree between the voice recognition result and the preset commands in the library is compared. When the matching degree reaches a certain threshold, the command recognition is determined to be successful, and a successful recognition prompt message is generated, which is usually manifested as a prompt sound or voice broadcast feedback from the charger. If the recognition is successful, charging curve No. 1 has been selected. If the match fails, the user will be asked to re-enter the voice command.

[0035] S60: According to the recognition success prompt information, confirm the target charging curve selected by the user, and obtain the target charging curve parameter information based on the target charging curve.

[0036] Specifically, once the voice command is successfully recognized, the charger extracts the specific parameter information corresponding to the charging curve from the charging curve library according to the name or number of the selected charging curve. These parameters include voltage, current, power, etc. By analyzing the characteristics of the target charging curve and the current battery status, the best charging method is automatically selected to ensure that the charging process is both efficient and safe.

[0037] S70: Based on the charging curve parameter information, adjust the charging power of the charger to adapt to the current charging state.

[0038] Specifically, the charger's main control MCU automatically adjusts the output voltage and current and changes the charging power according to the parameters of the confirmed target charging curve to adapt to the charging requirements of different batteries. For example, for lithium batteries, a relatively stable charging curve may be selected to avoid excessive current shocks, while for lead-acid batteries, a relatively fast charging method may be selected. These adjustments ensure the safety and efficiency of the charging process while meeting the requirements of different battery types.

[0039] In one embodiment, if Figure 2 As shown, in step S20, the initial charging curve parameter information includes: S201: Obtain charging status parameter information of the charger.

[0040] Specifically, the charging status parameter information includes battery voltage, battery current, temperature, load status, and battery health status.

[0041] S202: Determine an initial charging curve according to the charging state parameter information and a charging curve selection rule.

[0042] Specifically, after obtaining the charging status parameter information, the charger will analyze these data according to the preset charging curve selection rules. The design of the rules is based on multiple factors. First, the difference between the current voltage of the battery and the target charging voltage is used to evaluate the charging stage (such as constant current or constant voltage) to be selected. Secondly, the temperature parameters of the battery will also be taken into consideration. If the battery temperature is too high or too low, it may affect the selection of the charging curve to avoid the risk of overheating due to high temperature or low charging efficiency due to low temperature. In addition, the health status of the battery (such as internal resistance, number of charging cycles, etc.) and load status (such as device power requirements) will also be used as important bases for selecting the charging curve. For example, when the load is high, a higher current charging curve may be selected to ensure the stability and speed of charging, otherwise a lower current charging curve is selected. This step uses a rule algorithm to finally determine a preliminary charging curve by comprehensively analyzing these parameters.

[0043] S203: Based on the initial charging curve, acquiring charging curve parameter information corresponding to the initial charging curve from a charging curve library to obtain the initial charging curve parameter information.

[0044] Specifically, the charging curve library is a database that stores a variety of charging modes, including the optimal charging curves and parameters for different battery types and charging states. The determination of the initial charging curve is based on the working state and environmental factors of the battery. After selecting a suitable charging curve through rules, the charging curve library will be queried to find the charging parameter information corresponding to the curve. These parameter information usually includes but is not limited to the maximum charging voltage, the maximum charging current, the time point of constant current and constant voltage conversion during charging, the temperature control requirements of the battery in different charging stages, and the time control of different charging stages. These parameter values ​​in the charging curve library have been calibrated through a preset optimization algorithm and a large amount of measured data to ensure the efficiency of the charging process and the long life of the battery. Through these parameters, the charger can achieve precise control and adjust the charging current and voltage to adapt to the current battery status and environmental requirements, ensuring a smooth, safe and efficient charging process.

[0045] In one embodiment, if Figure 3 As shown, in step S202, the initial charging curve is determined according to the charging state parameter information and the charging curve selection rule, including: S2021: The charging curve selection rule is based on the following formula to obtain the initial charging curve: Where, C is the selected initial charging curve, C i is the i-th candidate charging curve in the charging curve library, T is the current battery temperature, T Ci is the optimal temperature range of the i-th charging curve, H is the current battery health information, and H Ciis the matching health state of the i-th charging curve, L is the current load state, and L Ci is the optimal load matching value of the i-th charging curve, V is the current battery voltage, V Ci is the target voltage of the i-th charging curve, α1 is the weight coefficient of T, α2 is the weight coefficient of H, α3 is the weight coefficient of L, and α4 is the weight coefficient of V.

[0046] Specifically, in the charging curve selection process, the current battery temperature T is first obtained, and the data is collected in real time through the built-in sensor according to the battery status, usually through a thermistor or thermocouple. When the battery temperature changes, the value will be continuously updated. Then, multiple candidate charging curves Ci are selected from the charging curve library, each of which defines an optimal operating temperature range T Ci For example, some charging curves may be suitable for a temperature range of 10°C to 40°C, while others may be suitable for different temperature ranges. Next, the temperature matching degree of each charging curve is obtained by calculating the difference between the current battery temperature and the temperature range of each candidate charging curve. The smaller the difference, the better the temperature matching degree. Then the battery health state H is obtained. The battery health state H evaluates the health of the battery based on data such as the number of battery charge and discharge cycles, battery capacity attenuation, and internal impedance. Each candidate charging curve Ci may correspond to a preset matching health state H Ci By comparing the current health status of the battery with the health adaptation value H of the charging curve Ci , calculate the difference in health status. The smaller the difference in the difference health status, the better the match between the battery health status and the charging curve. Next, obtain the load state L, which is a parameter that reflects the actual load condition of the battery during the charging process. The load state of the battery can be evaluated by real-time monitoring of the charger's power output and battery current. For example, when the charger needs to provide higher power, the load state L will increase. Each candidate charging curve also has a suitable load range L Ci In this load range, the charging curve performs best. By calculating (LL Ci ), the matching degree of the load state can be obtained. The smaller the difference, the better the load matching. At the same time, the battery voltage V is obtained through the voltage sensor, which is usually one of the most important parameters in the charging process. Each candidate charging curve also has a target voltage V Ci , indicating the voltage level that the charging curve hopes the battery will reach after charging. By comparing (VV Ci), the difference between the battery voltage and the target voltage of the candidate charging curve can be obtained. The smaller the difference, the better the voltage match. In each step, the matching degree of temperature, health status, load status and voltage will be multiplied by the corresponding weight coefficients α1, α2, α3 and α4, which determine the priority of each factor in selecting the charging curve. By taking the weighted sum of all candidate charging curves, the charging curve with the highest score is finally selected as the initial charging curve.

[0047] In one embodiment, if Figure 4 As shown, in step S40, the voice command information is processed by an offline voice recognition model to obtain a voice recognition result, including: S401: Perform voice feature extraction and acoustic decoding on the voice command information through an offline voice recognition model to obtain a voice recognition result.

[0048] Specifically, the user's voice command is first collected through a microphone and converted into a digital signal. Then, the offline speech recognition module preprocesses the digital signal, usually including noise suppression, speech enhancement, and signal framing. Then, a specific algorithm is used to extract features from each frame of the signal and convert the speech signal into a series of acoustic feature parameters. After feature extraction, the offline speech recognition module enters the acoustic decoding stage. Acoustic decoding maps these speech features into a set of possible phoneme sequences or vocabulary sequences. The decoding process usually uses a pre-trained acoustic model, which predicts the most likely phonemes or words based on the input acoustic features, and optimizes them based on the joint probability of the acoustic model and the language model, and finally obtains the recognition result of the voice command. The decoding process also considers the vocabulary order and grammatical rules in the language model to further improve the recognition accuracy. For example, when the user says "select curve 2" to the device, the offline speech recognition module first extracts the speech features of the two parts of "select" and "curve 2", then recognizes these words through acoustic decoding, and converts the words into text information, such as "select curve 2".

[0049] In one embodiment, if Figure 5 As shown, in step S50, the speech recognition result is compared with the preset voice instruction library. If the speech recognition result is successfully recognized by the preset voice instruction library, a recognition success prompt message is generated, including: S501: Calculate the similarity between the speech recognition result and the instructions in the preset speech instruction library to obtain the instruction similarity result.

[0050] Specifically, the speech recognition results are first converted into a standard text format to ensure that they can be compared with the instructions in the preset voice instruction library. Then, by selecting an appropriate text similarity calculation algorithm, such as cosine similarity or a semantic similarity analysis method based on deep learning, the speech recognition results are compared with each instruction in the preset instruction library. During the similarity calculation process, the algorithm will process the words, phrases and context in the text to generate a numerical value that represents the similarity between the speech recognition results and each instruction. The higher the similarity value, the higher the degree of match between the recognition result and the instruction in the instruction library.

[0051] S502: If the instruction similarity result exceeds the instruction matching threshold, it is confirmed that the speech recognition result successfully matches the instruction in the preset voice instruction library, and a recognition success prompt message is generated.

[0052] Specifically, when the user issues a voice command (for example, select charging curve No. 2), the voice signal will be converted into a feature vector, and then compared with the preset instructions in the instruction library to calculate the similarity score. If the score exceeds the preset instruction matching threshold, it means that the recognition result is highly matched with an instruction in the instruction library, and it can be confirmed that the voice command has been successfully recognized. The setting of the threshold is usually adjusted according to the actual use environment, the type of voice command, and the required accuracy to ensure effective recognition in different noise environments. Once the voice command is confirmed to match successfully, a successful recognition prompt message is generated, which is usually fed back to the user through the charger's display screen, voice broadcast or other prompt methods, such as through voice broadcast that charging curve No. 2 has been selected or displaying a successful selection on the display screen.

[0053] In one embodiment, if Figure 6 As shown, in step S502, if the instruction similarity result exceeds the instruction matching threshold, it is confirmed that the speech recognition result successfully matches the instruction in the preset voice instruction library, and a recognition success prompt message is generated, which also includes: S5021: If the instruction similarity result does not exceed the instruction matching threshold, a recognition failure prompt message is generated.

[0054] Specifically, the feature vector of the voice command is compared with each command in the command library, and a similarity score is calculated. If the similarity score is lower than a preset threshold (for example, 60%), the recognition result is considered not accurate or reliable enough. In order to ensure user experience, information about recognition failure will be fed back in a variety of ways. These methods can include voice announcements and visual prompts. For example, a voice announcement may say "Sorry, we failed to recognize your command" or a display screen may show "Recognition failed, please try again." The purpose of this is to ensure that the user knows clearly that the command was not successfully recognized and can reissue the command.

[0055] Furthermore, in order to avoid repeated misrecognition and improve user experience, some auxiliary guidance will be provided after voice recognition fails, such as reminding users to avoid background noise as much as possible when speaking commands, or providing simple voice command samples to help users improve the accuracy of command recognition the next time they operate. For example, if the command spoken by the user is not recognized due to noise or unclear pronunciation, voice feedback such as "Please try again clearly" or "Please say your command again" will be displayed to guide the user to operate again.

[0056] In one embodiment, if Figure 7 As shown, in step S60, target charging curve parameter information is obtained based on the target charging curve, including: S601: Based on a target charging curve, acquiring charging curve parameter information corresponding to the target charging curve from a charging curve library to obtain the target charging curve parameter information.

[0057] Specifically, according to the target charging curve selected by the user through voice commands, the number or identifier of the target curve will be identified, and the charging curve parameter information associated with the target charging curve will be searched in the charging curve library. The charging curve library is a database that pre-stores multiple charging curves and corresponding parameters (such as voltage, current, charging time, etc.). The parameters of each charging curve have been fully verified and tested to ensure effectiveness and safety in different environments and devices. During the search process, the parameter information matching the target curve is quickly retrieved by matching the identifier of the target charging curve (such as the curve number or name) with the charging curve identifier recorded in the library. These parameter information contains specific charging settings, which may involve multiple dimensions of data such as the upper limit of the charging current, the range of change of the charging voltage, and the time setting of different stages in the charging process. Once this information is successfully extracted, it will be used as the target charging curve parameter information for the subsequent charging process to adjust the required power and charging strategy. In this way, accurate control of the charging process is ensured while adapting to different charging needs selected by users.

[0058] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0059] In one embodiment, a charger control device based on voice recognition is provided, and the charger control device based on voice recognition corresponds to the charger control method based on voice recognition in the above embodiment. Figure 8As shown, the charger control device based on voice recognition includes a charger standby time information acquisition module, a standby time comparison and charging curve selection module, a voice command acquisition module, an offline voice recognition processing module, a voice recognition result and instruction library comparison module, a target charging curve confirmation and parameter acquisition module and a charging power adjustment module. The functional modules are described in detail as follows: A module for obtaining information about the standby time of a charger is used to obtain information about the standby time of a charger; A standby time comparison and charging curve selection module, used to compare the standby time information with a preset standby time threshold, and if the standby time information is greater than the preset standby time threshold, select the initial charging curve parameter information to adjust the output power of the charger; A voice command acquisition module, used to acquire user voice command information if the standby time information is less than a preset standby time threshold; The offline speech recognition processing module is used to process the speech command information through the offline speech recognition model to obtain the speech recognition result; The voice recognition result and command library comparison module is used to compare the voice recognition result with the preset voice command library. If the voice recognition result and the preset voice command library are successfully recognized, a recognition success prompt message is generated; A target charging curve confirmation and parameter acquisition module is used to confirm the target charging curve selected by the user according to the recognition success prompt information, and obtain the target charging curve parameter information based on the target charging curve; The charging power adjustment module is used to adjust the charging power of the charger based on the charging curve parameter information to adapt to the current charging state.

[0060] Optionally, the standby time comparison and charging curve selection module includes: The charging status acquisition submodule is used to obtain the charging status parameter information of the charger; A charging curve selection submodule is used to determine an initial charging curve according to charging state parameter information and a charging curve selection rule; The charging curve parameter extraction submodule is used to obtain charging curve parameter information corresponding to the initial charging curve from a charging curve library based on the initial charging curve, so as to obtain the initial charging curve parameter information.

[0061] Optionally, the charging curve selection submodule includes: The initial charging curve selection submodule is used to obtain the initial charging curve based on the following formula: Where, C is the selected initial charging curve, C i is the i-th candidate charging curve in the charging curve library, T is the current battery temperature, T Ciis the optimal temperature range of the i-th charging curve, H is the current battery health information, and H Ci is the matching health state of the i-th charging curve, L is the current load state, and L Ci is the optimal load matching value of the i-th charging curve, V is the current battery voltage, V Ci is the target voltage of the i-th charging curve, α1 is the weight coefficient of T, α2 is the weight coefficient of H, α3 is the weight coefficient of L, and α4 is the weight coefficient of V.

[0062] Optionally, the offline speech recognition processing module includes: The speech recognition submodule is used to extract speech features and acoustically decode the speech command information through an offline speech recognition model to obtain speech recognition results.

[0063] Optionally, the voice recognition result and instruction library comparison module includes: The voice command similarity calculation submodule is used to calculate the similarity between the voice recognition result and the command in the preset voice command library to obtain the command similarity result; The voice command matching confirmation submodule is used to confirm that the voice recognition result successfully matches the command in the preset voice command library if the command similarity result exceeds the command matching threshold, and generate a recognition success prompt message.

[0064] Optionally, the voice command matching confirmation submodule further includes: The voice command recognition failure prompt generation submodule is used to generate recognition failure prompt information if the command similarity result does not exceed the command matching threshold.

[0065] Optionally, the target charging curve confirmation and parameter acquisition module includes: The charging curve parameter acquisition submodule is used to acquire charging curve parameter information corresponding to the target charging curve from the charging curve library based on the target charging curve, so as to obtain the target charging curve parameter information.

[0066] For the specific definition of the charger control device based on voice recognition, please refer to the definition of the charger control method based on voice recognition above, which will not be repeated here. Each module in the above-mentioned charger control device based on voice recognition can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0067] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for a charging curve library. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a charger control method based on voice recognition is implemented.

[0068] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Get the charger's standby time information; The standby time information is compared with a preset standby time threshold, and if the standby time information is greater than the preset standby time threshold, the initial charging curve parameter information is selected to adjust the output power of the charger; If the standby time information is less than the preset standby time threshold, obtaining the user voice command information; Processing the voice command information through an offline voice recognition model to obtain a voice recognition result; The speech recognition result is compared with the preset speech instruction library. If the speech recognition result is successfully recognized with the preset speech instruction library, a recognition success prompt message is generated; According to the recognition success prompt information, confirm the target charging curve selected by the user, and obtain the target charging curve parameter information based on the target charging curve; Based on the charging curve parameter information, the charging power of the charger is adjusted to adapt to the current charging state.

[0069] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Get the charger's standby time information; The standby time information is compared with a preset standby time threshold, and if the standby time information is greater than the preset standby time threshold, the initial charging curve parameter information is selected to adjust the output power of the charger; If the standby time information is less than the preset standby time threshold, obtaining the user voice command information; Processing the voice command information through an offline voice recognition model to obtain a voice recognition result; The speech recognition result is compared with the preset speech instruction library. If the speech recognition result is successfully recognized with the preset speech instruction library, a recognition success prompt message is generated; According to the recognition success prompt information, confirm the target charging curve selected by the user, and obtain the target charging curve parameter information based on the target charging curve; Based on the charging curve parameter information, the charging power of the charger is adjusted to adapt to the current charging state.

[0070] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0071] Those skilled in the art 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. In actual applications, the above-mentioned functions can be distributed and 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.

[0072] 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 charger control method based on voice recognition, characterized in that: The charger control method based on voice recognition includes: Get the charger's standby time information; Comparing the standby time information with a preset standby time threshold, and if the standby time information is greater than the preset standby time threshold, selecting initial charging curve parameter information to adjust the output power of the charger; If the standby time information is less than the preset standby time threshold, obtaining user voice command information; Processing the voice command information through an offline voice recognition model to obtain a voice recognition result; Comparing the speech recognition result with a preset speech instruction library, and generating recognition success prompt information if the speech recognition result and the preset speech instruction library are successfully recognized; According to the recognition success prompt information, confirm the target charging curve selected by the user, and obtain target charging curve parameter information based on the target charging curve; Based on the charging curve parameter information, the charging power of the charger is adjusted to adapt to the current charging state.

2. The charger control method based on voice recognition according to claim 1, characterized in that: The initial charging curve parameter information includes: Obtaining charging status parameter information of the charger; Determine an initial charging curve according to the charging state parameter information and in combination with a charging curve selection rule; Based on the initial charging curve, charging curve parameter information corresponding to the initial charging curve is acquired from a charging curve library to obtain the initial charging curve parameter information.

3. The charger control method based on voice recognition according to claim 2, characterized in that: The determining the initial charging curve according to the charging state parameter information and in combination with a charging curve selection rule includes: The charging curve selection rule obtains the initial charging curve based on the following formula: Wherein, C is the selected initial charging curve, and C i is the i-th candidate charging curve in the charging curve library, T is the current battery temperature, and T Ci is the optimal temperature range of the i-th charging curve, H is the current battery health information, and H Ci is the matching health state of the i-th charging curve, L is the current load state, and L Ci is the optimal load matching value of the i-th charging curve, V is the current battery voltage, and V Ci is the target voltage of the i-th charging curve, α1 is the weight coefficient of T, α2 is the weight coefficient of H, α3 is the weight coefficient of L, and α4 is the weight coefficient of V.

4. The charger control method based on voice recognition according to claim 1, characterized in that: The step of processing the voice command information through an offline voice recognition model to obtain a voice recognition result includes: The offline speech recognition model is used to perform speech feature extraction and acoustic decoding on the speech instruction information to obtain the speech recognition result.

5. The charger control method based on voice recognition according to claim 1, characterized in that: The comparing the speech recognition result with the preset speech instruction library, and if the speech recognition result is successfully recognized with the preset speech instruction library, generating recognition success prompt information, includes: Calculating the similarity between the speech recognition result and the instructions in the preset speech instruction library to obtain an instruction similarity result; If the instruction similarity result exceeds the instruction matching threshold, it is confirmed that the speech recognition result successfully matches the instruction in the preset voice instruction library, and the recognition success prompt information is generated.

6. The charger control method based on voice recognition according to claim 5, characterized in that: If the instruction similarity result exceeds the instruction matching threshold, confirming that the speech recognition result successfully matches the instruction in the preset voice instruction library, and generating the recognition success prompt information, further comprising: If the instruction similarity result does not exceed the instruction matching threshold, a recognition failure prompt message is generated.

7. The charger control method based on voice recognition according to claim 1, characterized in that: The obtaining target charging curve parameter information based on the target charging curve includes: Based on the target charging curve, charging curve parameter information corresponding to the target charging curve is acquired from the charging curve library to obtain the target charging curve parameter information.

8. A charger control device based on voice recognition, characterized in that: The charger control device based on voice recognition comprises: A module for obtaining information about the standby time of a charger is used to obtain information about the standby time of a charger; A standby time comparison and charging curve selection module, used to compare the standby time information with a preset standby time threshold, and if the standby time information is greater than the preset standby time threshold, select the initial charging curve parameter information to adjust the output power of the charger; A voice command acquisition module, configured to acquire user voice command information if the standby time information is less than the preset standby time threshold; An offline speech recognition processing module is used to process the speech instruction information through an offline speech recognition model to obtain a speech recognition result; A voice recognition result and instruction library comparison module is used to compare the voice recognition result with a preset voice instruction library, and if the voice recognition result and the preset voice instruction library are successfully recognized, a recognition success prompt message is generated; A target charging curve confirmation and parameter acquisition module, used to confirm the target charging curve selected by the user according to the recognition success prompt information, and obtain the target charging curve parameter information based on the target charging curve; The charging power adjustment module is used to adjust the charging power of the charger based on the charging curve parameter information to adapt to the current charging state.

9. A computer device 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 steps of the charger control method based on voice recognition as claimed in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the charger control method based on voice recognition as claimed in any one of claims 1 to 7 are implemented.

Images