A method for controlling an AI assistant based on speech recognition

Abstract

The present application relates to a method for controlling an AI assistant based on voice recognition, and relates to the technical field of smart phones. The method comprises: when the AI ​​assistant of a first terminal is in an awake state, receiving voice information input by a user; converting the voice information into text information; obtaining a voice instruction based on text information matching; when the voice instruction is a first instruction, judging whether the first terminal has network connection capability; if the first terminal has network connection capability, identifying the type of network connection; if it is a mobile data connection, opening a network hotspot according to the first instruction; if it is a WiFi connection, not opening the network hotspot according to the first instruction and maintaining the WiFi connection, and playing a first voice prompt information; if the first terminal does not have network connection capability, not opening the network hotspot according to the first instruction and playing a second voice prompt information through the AI ​​assistant; after the second voice prompt information is confirmed by the user, scanning nearby WiFi and selecting WiFi for connection.

Description

Technical Field

[0001] The present application relates to the technical field of smart phones, and in particular to an AI assistant control method based on voice recognition. Background Art

[0002] With the development of mobile communication technology and wireless network technology, more and more smart devices have voice recognition functions, allowing users to control the various functions of the device through voice commands. Especially in portable devices such as smartphones and tablets, voice recognition has become a convenient way of interaction. Through mobile phone AI assistants with voice recognition technology, users can easily perform various tasks such as making calls, sending text messages, and searching for information. And with the development of technology and the enhancement of the processing power of smart devices, more and more smart devices support the use of mobile phone AI assistants without network.

[0003] Then some functions of smartphones are incompatible, or it can be understood that when function A is turned on, function B cannot be used. When the user wants to turn on function A of another device, the mobile phone AI assistant will turn off function B of the current device and turn on function A after recognition, causing inconvenience. Summary of the invention

[0004] In order to at least partially solve the above technical problems, the present application provides an AI assistant control method based on speech recognition.

[0005] In the first aspect, the present application provides an AI assistant control method based on speech recognition adopts the following technical solution.

[0006] A method for controlling an AI assistant based on speech recognition, applied to a first terminal, comprising:

[0007] When the AI ​​assistant of the first terminal is in an awake state, receiving voice information input by the user;

[0008] Converting the voice information into text information;

[0009] Obtaining voice instructions based on the text information matching;

[0010] When the voice instruction is a first instruction, determining whether the first terminal has a network connection capability; the first instruction is configured to enable the first terminal to open a network hotspot;

[0011] If the first terminal has network connection capability, identify the type of network connection; if it is a mobile data connection, open the network hotspot according to the first instruction; if it is a WiFi connection, do not open the network hotspot according to the first instruction and maintain the WiFi connection, and play the first voice prompt information;

[0012] If the first terminal does not have the ability to connect to the network, the network hotspot will not be opened according to the first instruction, and the second voice prompt message will not be played through the AI ​​assistant; after the second voice prompt message is confirmed by the user, the nearby WiFi will be scanned and the WiFi will be selected for connection.

[0013] By adopting the above technical solution, the technical solution of the present application receives the voice information input by the user through the awake state of the AI ​​assistant, and converts it into text information, and then matches the voice command that the user intends to express. When the user issues the "open personal hotspot" command, the AI ​​assistant will first determine whether the first terminal has network connection capability. When the first terminal has network connection capability, the connection type is further identified. If it is a mobile data connection, the network hotspot is opened according to the first instruction, thereby ensuring that the first terminal can be used as a hotspot for other devices while maintaining network connection. If it is a WiFi connection, the network hotspot is not opened and the WiFi connection is maintained, and the first voice prompt information is played to let the user confirm whether it is really necessary to open the hotspot, thereby avoiding the situation where the first terminal loses network connection capability due to disconnection of the WiFi connection. When the first terminal does not have network connection capability, the AI ​​assistant will not open the hotspot, but ask the user whether it needs to connect to WiFi by playing the second voice prompt information. After the user confirms that WiFi needs to be connected, it will automatically scan nearby WiFi networks and select the best WiFi for connection, thereby restoring network connection capability. It can improve the user experience when multiple devices are used at the same time.

[0014] Optionally, scan nearby WiFi and select WiFi to connect to, including:

[0015] After the second voice prompt message is confirmed by the user, the WiFi scanning module is triggered to start; the WiFi scanning module scans nearby WiFi;

[0016] Obtain WiFi information of each WiFi, including WiFi name, signal strength, security level, network speed, and historical connection times;

[0017] Each scanned WiFi is evaluated according to the preference condition; the preference condition formula is: ; Where a, b, c and d are weight coefficients; is the score of signal strength; Score the security level; Rating for network speed; is the score of the number of historical connections, and P is the total score;

[0018] Select the most matching WiFi from the evaluated WiFi list and record it as the WiFi to be connected; the most matching WiFi is the WiFi with the highest total score

[0019] Try to connect to the WiFi to be connected; if the connection is successful, maintain the connection of the currently selected WiFi to be connected; if the connection fails, select the next best matching WiFi to try to connect.

[0020] Optionally, the weight coefficient in the preference condition is changed according to the usage scenario, specifically including:

[0021] S301, determining whether a Bluetooth module of the first terminal is enabled; if the Bluetooth module is not enabled, enabling the Bluetooth module;

[0022] S302, using the Bluetooth module to detect the Bluetooth devices in the surrounding and determine whether they match the known devices; wherein, when identifying whether the Bluetooth devices in the surrounding match the known devices, it is determined by comparing the MAC addresses;

[0023] S303, identifying whether the WiFi network in the surrounding area matches the known network; when identifying whether the WiFi network in the surrounding area matches the known network, determining by comparing the SSID and BSSID;

[0024] S304, comprehensively determining the usage scenario of the first terminal based on the matching results of S302 and S303;

[0025] S305: Adjust the weight coefficient in the preference condition according to the usage scenario.

[0026] Optionally, if the Bluetooth module is not enabled, enabling the Bluetooth module includes:

[0027] When it is determined that the Bluetooth module needs to be activated, the Bluetooth module is controlled to enter a temporary pairing mode;

[0028] In the temporary pairing mode, the first terminal is only allowed to send a probe request but not to make an actual connection;

[0029] After the to-be-connected WiFi is successfully connected, if the Bluetooth module is activated in S301 , the Bluetooth module is turned off again.

[0030] Optionally, after opening the network hotspot according to the first instruction, the method further includes:

[0031] S501, real-time monitoring of the signal quality and network load of the connected device; wherein S501 includes: measuring the signal strength of the connected device, monitoring the amount of data uploaded and downloaded by the connected device and the network delay;

[0032] S502, analyzing network requirements according to the monitored signal quality and network load;

[0033] S503: Based on the network demand analysis result, dynamically adjust the transmission power of the hotspot to meet the current network demand.

[0034] Optionally, after selecting WiFi for connection, the method further includes:

[0035] Performing activity detection through the first terminal to determine whether the user is using the first terminal;

[0036] Monitoring network traffic activity of the first terminal to determine whether there is data transmission greater than a preset data volume;

[0037] Determine whether it is a temporary WiFi based on the WiFi information; if so, obtain the remark information of the connected WiFi; the remark information includes the automatic shutdown duration of the WiFi, which is recorded as the first duration; when the connected WiFi is a temporary WiFi and it is detected that the user is not using the first terminal and there is no data transmission greater than a preset data volume, terminate the WiFi connection of the first terminal at an interval of a second duration, and the second duration is less than the first duration; if the user is again monitored to use the first terminal during the second duration, re-establish the WiFi connection and maintain the WiFi connection;

[0038] If it is determined that it is not a temporary WiFi, then when it is determined that the user is not using the first terminal and there is no data transmission greater than the preset data volume, the WiFi connection of the first terminal is terminated; when the user is monitored to use the first terminal again, the WiFi connection is re-established and maintained.

[0039] Optionally, the activity detection includes:

[0040] Use the accelerometer to detect whether the device is moving;

[0041] Detecting whether the screen is on; and,

[0042] Detects whether there is key or touch screen input.

[0043] On the second aspect, the present application provides an AI assistant control system based on speech recognition adopts the following technical solution.

[0044] An AI assistant control system based on speech recognition, comprising:

[0045] The first processing module is used to: when the AI ​​assistant of the first terminal is in the awake state, receive the voice information input by the user;

[0046] A second processing module is used to: convert the voice information into text information;

[0047] A third processing module is used to: obtain a voice instruction based on the text information matching;

[0048] A fourth processing module is used to: when the voice instruction is a first instruction, determine whether the first terminal has a network connection capability; the first instruction is configured to enable the first terminal to open a network hotspot;

[0049] a fifth processing module, configured to: if the first terminal has network connection capability, identify the type of network connection; if it is a mobile data connection, open the network hotspot according to the first instruction; if it is a WiFi connection, do not open the network hotspot according to the first instruction and maintain the WiFi connection, and play the first voice prompt information;

[0050] The sixth processing module is used for: if the first terminal does not have the network connection capability, not opening the network hotspot according to the first instruction and playing the second voice prompt information through the AI ​​assistant; after the second voice prompt information is confirmed by the user, scanning nearby WiFi and selecting WiFi for connection.

[0051] In a third aspect, the present application discloses an electronic device, comprising a memory and a processor, wherein the memory stores a computer program that is loaded by the processor and executes any of the above methods.

[0052] In a fourth aspect, the present application discloses a computer-readable storage medium storing a computer program that can be loaded by a processor and execute any of the above methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a flow chart of an AI assistant control method based on speech recognition according to an embodiment of the present application;

[0054] Figure 2 This is a system block diagram of an AI assistant control system based on speech recognition in an embodiment of the present application;

[0055] In the figure, 201 is a first processing module; 202 is a second processing module; 203 is a third processing module; 204 is a fourth processing module; 205 is a fifth processing module; and 206 is a sixth processing module. DETAILED DESCRIPTION

[0056] The following is combined with Figure 1-2 The present application is further described with specific embodiments.

[0057] Reference Figure 1When multiple smart devices are used, it may cause the device that the user does not expect to operate to be misoperated. When the smart device turns on the mobile hotspot function, the smart device cannot connect to WiFi. In some cases, the user has at least two smart devices, A and B, and expects to use device A to open a WiFi hotspot for device B, but device B cannot connect to the Internet. Since WiFi hotspots are generally not set to be always open, and WiFi connections are often set to be always open by users, when the user issues an instruction to turn on the hotspot, if devices A and B recognize it at the same time, device B will also turn on the hotspot, so that the WiFi function of device B will be temporarily turned off, and the connection between devices A and B cannot be automatically recognized. The user needs to click on device B again to operate, which reduces the user experience.

[0058] The present application embodiment discloses an AI assistant control method based on speech recognition. Figure 1 , a method for controlling an AI assistant based on speech recognition, applied to a first terminal, comprising the following steps:

[0059] Step 101, when the AI ​​assistant of the first terminal is in the awake state, receive the voice information input by the user. Specifically, the first terminal is a device for executing the method of the present invention, and the first terminal is an intelligent device with voice recognition function and supporting network connection, such as a smart phone, tablet computer, smart watch or other similar portable electronic device. The AI ​​assistant is an intelligent assistant program embedded in the first terminal, which can receive the user's voice instructions through voice recognition technology and perform corresponding operations according to the instructions. The functions of the AI ​​assistant include voice recognition, voice instruction parsing and performing corresponding operations according to the instructions. The user activates the AI ​​assistant to enter the awake state through a specific wake-up word or button. In the awake state, the AI ​​assistant can receive the user's voice input and perform subsequent processing.

[0060] Step 102: Convert the voice information into text information.

[0061] Specifically, voice information is converted into text information after speech recognition processing, and the text information is used for subsequent voice command matching so that the AI ​​assistant can understand the user's intentions.

[0062] Step 103: obtain voice instructions based on the text information matching.

[0063] Step 104: When the voice instruction is a first instruction, determine whether the first terminal has network connection capability; the first instruction is configured to enable the first terminal to open a network hotspot.

[0064] Specifically, the first instruction is to turn on the wireless hotspot. In some cases, the first instruction is matched when the user says "turn on personal hotspot", "hotspot turned on", etc. The above network connection capability can be understood as whether the first terminal can currently connect to the Internet. The connection method can be WiFi connection or cellular network connection (i.e., mobile data connection).

[0065] Step 105: If the first terminal has network connection capability, identify the type of network connection; if it is a mobile data connection, open the network hotspot according to the first instruction; if it is a WiFi connection, do not open the network hotspot according to the first instruction and maintain the WiFi connection, and play the first voice prompt information.

[0066] Specifically, when the type of network connection is a mobile data connection, opening the network hotspot according to the first instruction will not cause the device to disconnect from the WiFi connection after the hotspot is turned on. If the first terminal is connected to WiFi, the conventional AI assistant will turn on the device hotspot, and the first terminal will disconnect from the WiFi connection. If the first terminal itself is unable to connect to the Internet through the cellular network, it will cause the first terminal to be unable to connect to the Internet and the configured hotspot will not have the ability to connect to the network. At this time, the AI ​​assistant will play the first voice prompt information to the user for confirmation. After the user confirms not to turn on the hotspot, the WiFi connection is maintained; after the user confirms to turn on the hotspot, the network hotspot is turned on.

[0067] Step 106: If the first terminal does not have network connection capability, the network hotspot is not opened according to the first instruction and the second voice prompt message is not played through the AI ​​assistant; after the second voice prompt message is confirmed by the user, the nearby WiFi is scanned and the WiFi is selected for connection.

[0068] Specifically, if the first terminal does not have network connection capability, then the first instruction is likely to configure other devices to open a hotspot for use by the first terminal. At this time, the first terminal plays a second voice prompt message through the AI ​​assistant, asking the user to confirm whether to connect to the hotspot, and then the instruction to open the hotspot is based on the network environment and user confirmation to connect to the network.

[0069] In summary, the technical solution of the present application receives the voice information input by the user through the awake state of the AI ​​assistant, converts it into text information, and then matches the voice command that the user intends to express. When the user issues the "open personal hotspot" command, the AI ​​assistant will first determine whether the first terminal has network connection capability. When the first terminal has network connection capability, the connection type is further identified. If it is a mobile data connection, the network hotspot is opened according to the first instruction, thereby ensuring that the first terminal can be used as a hotspot for other devices while maintaining network connection. If it is a WiFi connection, the network hotspot is not opened and the WiFi connection is maintained, and the first voice prompt information is played to let the user confirm whether it is really necessary to open the hotspot, thereby avoiding the situation where the first terminal loses network connection capability due to disconnection of the WiFi connection. When the first terminal does not have network connection capability, the AI ​​assistant will not open the hotspot, but ask the user whether it needs to connect to WiFi by playing the second voice prompt information. After the user confirms that WiFi needs to be connected, it will automatically scan nearby WiFi networks and select the best WiFi for connection, thereby restoring network connection capability. It can improve the user experience when multiple devices are used at the same time.

[0070] As a specific implementation of an AI assistant control method based on voice recognition, scanning nearby WiFi and selecting WiFi for connection includes:

[0071] After the second voice prompt message is confirmed by the user, the WiFi scanning module is triggered to start; the WiFi scanning module scans nearby WiFi;

[0072] Obtain WiFi information of each WiFi, including WiFi name, signal strength, security level, network speed, and historical connection times;

[0073] Each scanned WiFi is evaluated according to the preference condition; the preference condition formula is: ; Where a, b, c and d are weight coefficients; is the score of signal strength; Score the security level; Rating for network speed; is the score of the number of historical connections, and P is the total score;

[0074] Select the most matching WiFi from the evaluated WiFi list and record it as the WiFi to be connected;

[0075] Try to connect to the WiFi to be connected; if the connection is successful, maintain the connection of the currently selected WiFi to be connected; if the connection fails, select the next best matching WiFi to try to connect.

[0076] Specifically, after the second voice prompt information is confirmed by the user, the WiFi scanning module is triggered to start, and the WiFi scanning module begins to scan nearby WiFi networks; the first terminal obtains WiFi information of each WiFi, including WiFi name, signal strength, security level, network speed and historical connection times; each scanned WiFi is evaluated; according to the evaluation result, the most matching WiFi is selected from the WiFi list and recorded as the WiFi to be connected; then try to connect to the WiFi to be connected; if the connection is successful, maintain the connection of the currently selected WiFi to be connected; if the connection fails, select the next most matching WiFi to try to connect, to ensure that the first terminal can automatically select and connect to the optimal WiFi network.

[0077] As a specific implementation of an AI assistant control method based on speech recognition, the weight coefficient in the preference condition changes according to the usage scenario, specifically including:

[0078] S301, determining whether a Bluetooth module of the first terminal is enabled; if the Bluetooth module is not enabled, enabling the Bluetooth module;

[0079] S302, using the Bluetooth module to detect the Bluetooth devices in the surrounding and determine whether they match the known devices; wherein, when identifying whether the Bluetooth devices in the surrounding match the known devices, it is determined by comparing the MAC addresses;

[0080] S303, identifying whether the WiFi network in the surrounding area matches the known network; when identifying whether the WiFi network in the surrounding area matches the known network, determining by comparing the SSID and BSSID;

[0081] S304, comprehensively determining the usage scenario of the first terminal based on the matching results of S302 and S303;

[0082] S305: Adjust the weight coefficient in the preference condition according to the usage scenario.

[0083] Specifically, determine whether the Bluetooth module of the first terminal is enabled, and if not, enable the Bluetooth module; use the Bluetooth module to detect surrounding Bluetooth devices, and determine whether they match known devices by comparing MAC addresses; identify surrounding WiFi networks, and determine whether they match known networks by comparing SSID and BSSID; based on the above matching results, comprehensively determine the usage scenario of the first terminal, adjust the weight coefficient in the preference condition according to the determined usage scenario, and intelligently adjust the priority of WiFi selection in different scenarios, so that the first terminal can more accurately select the optimal WiFi network for connection, thereby improving the intelligence of network connection and user experience.

[0084] As a specific implementation of an AI assistant control method based on voice recognition, if the Bluetooth module is not enabled, enabling the Bluetooth module includes:

[0085] When it is determined that the Bluetooth module needs to be activated, the Bluetooth module is controlled to enter a temporary pairing mode;

[0086] In the temporary pairing mode, the first terminal is only allowed to send a probe request but not to make an actual connection;

[0087] After the to-be-connected WiFi is successfully connected, if the Bluetooth module is activated in S301 , the Bluetooth module is turned off again.

[0088] Specifically, when it is determined that the Bluetooth module needs to be activated, the Bluetooth module is controlled to enter a temporary pairing mode; in the temporary pairing mode, the first terminal is only allowed to send a detection request but not to make an actual connection; after the to-be-connected WiFi connection is successful, if the Bluetooth module is activated by S301, the Bluetooth module is turned off again. When Bluetooth is needed to detect the environment, the Bluetooth module can safely perform the detection task without establishing unnecessary connections, thereby restoring the network connection capability while protecting user privacy and device security.

[0089] As one implementation of an AI assistant control method based on voice recognition, after opening the network hotspot according to the first instruction, the method further includes:

[0090] S501, real-time monitoring of the signal quality and network load of the connected device; wherein S501 includes: measuring the signal strength of the connected device, monitoring the amount of data uploaded and downloaded by the connected device and the network delay;

[0091] S502, analyzing network requirements according to the monitored signal quality and network load;

[0092] S503: Based on the network demand analysis result, dynamically adjust the transmission power of the hotspot to meet the current network demand.

[0093] Specifically, after the network hotspot is turned on according to the first instruction, the signal quality and network load of the connected device are monitored in real time; the network demand is analyzed according to the monitored signal quality and network load; based on the results of the network demand analysis, the transmission power of the hotspot is dynamically adjusted to meet the current network demand. After the network hotspot is turned on, the hotspot performance can be dynamically optimized according to the actual situation of the connected device, thereby improving the stability and efficiency of the network connection.

[0094] As one implementation of an AI assistant control method based on voice recognition, after selecting WiFi for connection, the method further includes:

[0095] Performing activity detection through the first terminal to determine whether the user is using the first terminal;

[0096] Monitoring network traffic activity of the first terminal to determine whether there is data transmission greater than a preset data volume;

[0097] Determine whether it is a temporary WiFi based on WiFi information; if so, obtain the remark information of the connected WiFi; the remark information includes the automatic shutdown duration of the WiFi, which is recorded as the first duration; when it is determined that the user is not using the first terminal and there is no data transmission greater than a preset data volume, terminate the WiFi connection of the first terminal after a second duration; when it is detected that the user is using the first terminal again, re-establish the WiFi connection and maintain the WiFi connection;

[0098] If it is determined that it is not a temporary WiFi, then when it is determined that the user is not using the first terminal and there is no data transmission greater than the preset data volume, the WiFi connection of the first terminal is terminated; when the user is monitored to use the first terminal again, the WiFi connection is re-established and maintained.

[0099] As one implementation of an AI assistant control method based on voice recognition, after selecting WiFi for connection, the method further includes:

[0100] Performing activity detection through the first terminal to determine whether the user is using the first terminal;

[0101] Monitoring network traffic activity of the first terminal to determine whether there is data transmission greater than a preset data volume;

[0102] Determine whether it is a temporary WiFi based on WiFi information; if so, obtain the remark information of the connected WiFi; the remark information includes the automatic shutdown duration of WiFi, which is recorded as the first duration; when the connected WiFi is a temporary WiFi and it is detected that the user is not using the first terminal and there is no data transmission greater than the preset data volume, the WiFi connection of the first terminal is terminated at an interval of a second duration, and the second duration is less than the first duration; if the user is again monitored to use the first terminal during the second duration, the WiFi connection is re-established and the WiFi connection is maintained. Specifically, the above-mentioned second duration is less than the first duration, which can be understood as the starting time of the second duration is a, the final time is b, and both times a and b are within the first duration; at time a, it is detected that the user is not using the first terminal and there is no data transmission greater than the preset data volume, and the WiFi connection is interrupted at this time, and the WiFi connection is re-established at time b, thereby avoiding the WiFi connection interruption time being too long to cause the temporary WiFi to be closed; if it is still detected that the user is not using the first terminal and there is no data transmission greater than the preset data volume at time b, the WiFi connection is interrupted again, and the WiFi connection is established again after the second duration.

[0103] If it is determined that it is not a temporary WiFi, then when it is determined that the user is not using the first terminal and there is no data transmission greater than the preset data volume, the WiFi connection of the first terminal is terminated; when the user is monitored to use the first terminal again, the WiFi connection is re-established and maintained.

[0104] Specifically, it automatically disconnects when the user is inactive and there is no important data transmission, thereby saving power resources, and quickly restores the connection when the user uses the device again, improving the energy saving effect of the device.

[0105] As one implementation of an AI assistant control method based on speech recognition, the activity detection includes:

[0106] Use the accelerometer to detect whether the device is moving;

[0107] Detecting whether the screen is on; and,

[0108] Detects whether there is key or touch screen input.

[0109] Reference Figure 2 The present application also provides an AI assistant control system based on speech recognition, as one implementation of an AI assistant control system based on speech recognition, including:

[0110] The first processing module 201 is used to: when the AI ​​assistant of the first terminal is in the awake state, receive the voice information input by the user;

[0111] The second processing module 202 is used to convert the voice information into text information;

[0112] The third processing module 203 is used to: obtain a voice instruction based on the text information matching;

[0113] The fourth processing module 204 is used to: when the voice instruction is a first instruction, determine whether the first terminal has a network connection capability; the first instruction is configured to enable the first terminal to open a network hotspot;

[0114] The fifth processing module 205 is used to: if the first terminal has a network connection capability, identify the type of network connection; if it is a mobile data connection, open the network hotspot according to the first instruction; if it is a WiFi connection, do not open the network hotspot according to the first instruction and maintain the WiFi connection, and play the first voice prompt information;

[0115] The sixth processing module 206 is used for: if the first terminal does not have the network connection capability, not opening the network hotspot according to the first instruction and playing the second voice prompt information through the AI ​​assistant; after the second voice prompt information is confirmed by the user, scanning nearby WiFi and selecting WiFi for connection.

[0116] The embodiment of the present application also discloses an electronic device.

[0117] Specifically, the device includes a memory and a processor, and the memory stores a computer program that can be loaded by the processor and execute any of the above-mentioned AI assistant control methods based on voice recognition.

[0118] The embodiment of the present application also discloses a computer-readable storage medium. Specifically, the computer-readable storage medium stores a computer program that can be loaded by a processor and execute any of the above-mentioned AI assistant control methods based on voice recognition, and the computer-readable storage medium includes, for example: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0119] It should be noted that the above embodiments are only used to illustrate the present application and are not intended to limit the technical solutions described in the present application. Although the present application has been described in detail in this specification with reference to the above embodiments, a person of ordinary skill in the art should understand that a person of ordinary skill in the art can still modify or make equivalent substitutions to the present application, and all technical solutions and improvements thereof that do not depart from the spirit and scope of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for controlling an AI assistant based on speech recognition, applied to a first terminal, characterized in that: include: When the AI ​​assistant of the first terminal is in an awake state, receiving voice information input by the user; Converting the voice information into text information; Obtaining voice instructions based on the text information matching; When the voice instruction is a first instruction, determining whether the first terminal has a network connection capability; the first instruction is configured to enable the first terminal to open a network hotspot; If the first terminal has network connection capability, identifying the type of network connection; If it is a mobile data connection, opening the network hotspot according to the first instruction; If it is a WiFi connection, then the network hotspot is not opened according to the first instruction and the WiFi connection is maintained, and the first voice prompt information is played; If the first terminal does not have the ability to connect to the network, the network hotspot will not be opened according to the first instruction, and the second voice prompt message will not be played through the AI ​​assistant; after the second voice prompt message is confirmed by the user, the nearby WiFi will be scanned and WiFi will be selected for connection.

2. The AI ​​assistant control method based on speech recognition according to claim 1, characterized in that: Scan nearby WiFi and select WiFi to connect to, including: After the second voice prompt message is confirmed by the user, the WiFi scanning module is triggered to start; the WiFi scanning module scans nearby WiFi; Obtain WiFi information of each WiFi, including WiFi name, signal strength, security level, network speed, and historical connection times; Each scanned WiFi is evaluated according to the preference condition; the preference condition formula is: ; Where a, b, c and d are weight coefficients; is the score of signal strength; Score the security level; Rating of network speed; is the score of the number of historical connections, and P is the total score; Select the most matching WiFi from the evaluated WiFi list and record it as the WiFi to be connected; Try to connect to the WiFi to be connected; if the connection is successful, maintain the connection of the currently selected WiFi to be connected; if the connection fails, select the next best matching WiFi to try to connect.

3. The AI ​​assistant control method based on speech recognition according to claim 2, characterized in that: The weight coefficients in the preference conditions vary according to the usage scenario, specifically including: S301, determining whether a Bluetooth module of the first terminal is enabled; if the Bluetooth module is not enabled, enabling the Bluetooth module; S302, using the Bluetooth module to detect the Bluetooth devices in the surrounding and determine whether they match the known devices; wherein, when identifying whether the Bluetooth devices in the surrounding match the known devices, it is determined by comparing the MAC addresses; S303, identifying whether the WiFi network in the surrounding area matches the known network; when identifying whether the WiFi network in the surrounding area matches the known network, determining by comparing the SSID and BSSID; S304, comprehensively determining the usage scenario of the first terminal based on the matching results of S302 and S303; S305: Adjust the weight coefficient in the preference condition according to the usage scenario.

4. The AI ​​assistant control method based on speech recognition according to claim 3, characterized in that: If the Bluetooth module is not enabled, enabling the Bluetooth module includes: When it is determined that the Bluetooth module needs to be activated, the Bluetooth module is controlled to enter a temporary pairing mode; In the temporary pairing mode, the first terminal is only allowed to send a probe request but not to make an actual connection; After the to-be-connected WiFi is successfully connected, if the Bluetooth module is activated by S301 , the Bluetooth module is turned off again.

5. The AI ​​assistant control method based on speech recognition according to claim 4, characterized in that: After opening the network hotspot according to the first instruction, the method further includes: S501, real-time monitoring of the signal quality and network load of the connected device; wherein S501 includes: measuring the signal strength of the connected device, monitoring the amount of data uploaded and downloaded by the connected device and the network delay; S502, analyzing network requirements according to the monitored signal quality and network load; S503: Based on the network demand analysis result, dynamically adjust the transmission power of the hotspot to meet the current network demand.

6. The AI ​​assistant control method based on speech recognition according to claim 5, characterized in that: After selecting WiFi for connection, the method further includes: Performing activity detection through the first terminal to determine whether the user is using the first terminal; Monitoring network traffic activity of the first terminal to determine whether there is data transmission greater than a preset data volume; Determine whether it is a temporary WiFi based on the WiFi information; if so, obtain the remark information of the connected WiFi; the remark information includes the automatic shutdown duration of the WiFi, which is recorded as the first duration; when the connected WiFi is a temporary WiFi and it is detected that the user is not using the first terminal and there is no data transmission greater than a preset data volume, terminate the WiFi connection of the first terminal at an interval of a second duration, and the second duration is less than the first duration; if the user is again monitored to use the first terminal during the second duration, re-establish the WiFi connection and maintain the WiFi connection; If it is determined that it is not a temporary WiFi, then when it is determined that the user is not using the first terminal and there is no data transmission greater than the preset data volume, the WiFi connection of the first terminal is terminated; when the user is monitored to use the first terminal again, the WiFi connection is re-established and maintained.

7. The AI ​​assistant control method based on speech recognition according to claim 6, characterized in that: The activity detection includes: Use the accelerometer to detect whether the device is moving; Detecting whether the screen is on; and, Detects whether there is key or touch screen input.

Images