A smart home dialogue optimization method, device, equipment and storage medium

Abstract

The application relates to the technical field of smart home, and discloses a smart home dialogue optimization method, device, equipment and storage medium, the method comprises the following steps: acquiring user authorization information sent by smart control equipment of each room; in response to the user authorization information, identifying a target smart control equipment with a low usage rate; acquiring user voice information continuously received by each target smart control equipment within a preset time length; identifying a real intention of a user according to the user voice information; and adjusting a standard dialogue and a dialogue response strategy of the target smart control equipment according to the real intention of the user. The application solves the problem that smart home dialogue optimization is not timely.

Description

Technical Field

[0001] This invention relates to the field of smart home technology, specifically to a method, apparatus, device, and storage medium for optimizing smart home communication messages. Background Technology

[0002] Currently, in the long-term rental industry, real estate agencies are gradually renovating properties and installing smart home systems to improve the user experience. To control these smart devices, each room is equipped with smart control equipment to receive and process user voice commands, determining the user's intent and controlling corresponding devices inside and outside the room to perform actions. However, sometimes users' spoken language is not standard and differs from the standard terminology stored in the smart control devices, causing the smart devices to fail to perform the desired actions or to perform actions that are not what the user wants. The current mainstream solution involves receiving user feedback through various channels, and real estate agencies then optimize based on this feedback. However, optimizing the smart devices' communication based on user feedback is cumbersome for agencies. The main problem is that many users are reluctant to provide feedback, leading to unresolved issues with the smart home and control devices. Users find them difficult to use, resulting in increasingly high abandonment rates and a waste of smart control functionality.

[0003] Therefore, there is an urgent need for a solution that can accurately and automatically optimize smart home communication messages to improve the utilization rate of smart control functions. Summary of the Invention

[0004] In view of this, the present invention provides a method, apparatus, device and storage medium for optimizing smart home dialogue, in order to solve the problem of untimely optimization of smart home dialogue.

[0005] In a first aspect, the present invention provides a method for optimizing smart home dialogue, the method comprising: acquiring user authorization information sent by smart control devices in each room; in response to the user authorization information, identifying target smart control devices with low usage rates; acquiring user voice information continuously received by each of the target smart control devices within a preset time period; identifying the user's true intent based on the user voice information; and adjusting the standard dialogue and dialogue response strategy of the target smart control devices based on the user's true intent.

[0006] In an optional embodiment, the identifying a target intelligent control device with a low usage rate in response to the user authorization information includes: acquiring a reference date; counting the number of retained devices each day from the reference date to a preset number of days later, where the number of retained devices is the number of intelligent control devices that are active on both the reference date and the statistical date, and the statistical date is any date within the preset number of days; determining a target date on which the number of retained devices is less than a preset threshold from the statistical dates according to the number of retained devices on each day; and detecting intelligent control devices that are inactive within all the target dates, and taking the detected intelligent control devices as the target intelligent control device.

[0007] In an optional embodiment, the acquiring user voice information continuously received by each of the target intelligent control devices within a preset time length includes: detecting interaction records of each of the target intelligent control devices, and acquiring from the interaction records the user voice information with more than three dialogues occurring within one minute.

[0008] In an optional embodiment, the identifying the true user intention according to the user voice information includes: when the user voice information indicates that the user continuously controls two or more smart home devices, the true user intention is multi-device linkage control; when the user voice information indicates that a corresponding smart home device does not exist in the corresponding room, the true user intention is to control the device according to naming habits; when the user voice information indicates that the corresponding smart home device does not exist in the current room but exists in other rooms, the true user intention is to control the device according to the device name.

[0009] In an optional embodiment, when the true user intention is multi-device linkage control, the adjusting the standard speech and speech response strategy of the target intelligent control device according to the true user intention includes: determining a plurality of target smart home devices under continuous control from the user voice information; determining a first speech command according to the first piece of voice information including the target smart home device received in the user voice information; setting a linkage control instruction for the plurality of target smart home devices; binding the first speech command and the linkage control instruction, and burning the binding result into the target intelligent control device.

[0010] In an optional implementation, when the user's true intention is to control the device according to their naming habits, adjusting the standard dialogue and dialogue response strategy of the target smart control device according to the user's true intention includes: extracting room name information from the user's voice information; determining the target smart home device to be controlled from the user's voice information; determining the target name information from the standard room name and smart home device corresponding information stored in the target smart control device; and replacing the target name information in the target smart control device with the room name information.

[0011] In an optional implementation, when the user's true intent is to control the device by device name, adjusting the standard dialogue and dialogue response strategy of the target smart control device according to the user's true intent includes: determining the target voice information that successfully controls the smart home device from the user's voice information; parsing the target voice information to obtain the target smart home device controlled by the target voice information; determining a second dialogue command based on a first voice message containing the target smart home device received in the user's voice information; associating the second dialogue command with the target smart home device, and burning the association result into the target smart control device.

[0012] Secondly, the present invention provides a smart home dialogue optimization device, the device comprising: an authorization module for acquiring user authorization information sent by smart control devices in each room; a device monitoring module for identifying target smart control devices with low usage rates in response to the user authorization information; a voice information acquisition module for acquiring user voice information continuously received by each of the target smart control devices within a preset time period; a cause identification module for identifying the user's true intent based on the user voice information; and an adjustment module for adjusting the standard dialogue and dialogue response strategy of the target smart control devices based on the user's true intent.

[0013] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method described in the first aspect or any corresponding embodiment thereof.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the method described in the first aspect or any corresponding embodiment thereof.

[0015] The technical solution provided by the embodiments of the present invention has the following advantages:

[0016] Under user authorization, this invention automatically acquires user voice information received continuously by each low-usage target smart control device within a preset time period by identifying such devices. Based on this voice information, the true intent of the user controlling the low-usage target smart control device is identified, making it easier to analyze the underlying reasons for the low usage rate. Finally, based on the identified true user intent, the standard script and script response strategy of the target smart control device are adjusted according to a preset adjustment scheme. This improves the accuracy of the target smart control device in recognizing user voice and the accuracy of executing actions without user feedback, thereby enhancing the timeliness of smart home script optimization.

[0017] In addition, embodiments of the present invention determine the target intelligent control devices with low usage by calculating the number of devices remaining, thereby improving the accuracy of target intelligent control device identification.

[0018] In addition, the embodiments of the present invention have automatically and accurately identified three types of users' true intentions at the level of dialogue: multi-device linkage control, control of devices according to address habits, and control of devices according to device names, and provided corresponding adjustment measures, which further improves the accuracy of automatically adjusting smart home dialogue. Attached Figure Description

[0019] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating a smart home dialogue optimization method according to an embodiment of the present invention;

[0021] Figure 2 This is a schematic diagram of the user voice information collection interface according to an embodiment of the present invention;

[0022] Figure 3 This is a schematic diagram of another interface for collecting user voice information according to an embodiment of the present invention;

[0023] Figure 4 This is a schematic diagram of another user voice information collection interface according to an embodiment of the present invention;

[0024] Figure 5 This is a schematic diagram of the structure of a smart home dialogue optimization device according to an embodiment of the present invention;

[0025] Figure 6This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] According to an embodiment of the present invention, a method for optimizing smart home dialogue is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0028] This embodiment provides a method for optimizing smart home communication scripts, which can be used with the aforementioned computer equipment. Figure 1 This is a flowchart of a smart home dialogue optimization method according to an embodiment of the present invention, the process including the following steps:

[0029] Step S101: Obtain user authorization information sent by the smart control devices in each room.

[0030] Specifically, the intelligent control device is a relay device deployed in each room to receive user voice and issue commands to the smart home system. The intelligent control device can be a smart speaker, a smart screen, etc., and this embodiment is only an example and not a limitation. This embodiment of the invention collects user voice information from the user's room through the intelligent control device, and then implements a scheme to automatically optimize the script based on the collected user voice information. First, when the user uses the intelligent control device for the first time, they need to agree to the improvement plan by clicking, inputting, etc., thereby sending the generated user authorization information to the server to authorize the server to collect the user's voice information.

[0031] Step S102: In response to user authorization information, identify target smart control devices with low usage rates.

[0032] Specifically, based on the received user authorization information, the server recognizes that the smart control device that sent the authorization information has agreed to collect the user's voice information, and thus optimizes the script for these smart control devices. However, optimizing all smart control devices is problematic in two ways: firstly, it lacks specificity and the optimization results are inaccurate, because some users find the smart control devices difficult to use, while others find them easy to use. Optimizing the scripts for users who find them easy to use doesn't significantly help those who find them difficult to use and fails to address the core issues; secondly, the optimization workload is large, resulting in low efficiency. Therefore, this embodiment of the invention identifies each smart control device and pinpoints the target smart control devices with lower usage rates. Users who find the smart control devices difficult to use are primarily concentrated in the user groups corresponding to these low-usage target smart control devices, thus allowing for targeted script optimization, which further improves the accuracy of the optimization.

[0033] Step S103: Obtain user voice information continuously received by each target intelligent control device within a preset time period.

[0034] Specifically, to further improve the accuracy and relevance of speech optimization, this embodiment of the invention does not utilize all collected user voice information for optimization. Instead, it collects user voice information continuously received by the target smart control device within a preset time period for cause analysis and optimization. For example, the preset time period can be a short duration such as 30 seconds, 1 minute, or 2 minutes. The reason for proposing this optimization scheme is that this embodiment of the invention considers that when users cannot perform the corresponding action in the smart home or the action performed is not the action the user wants, they will repeat their commands multiple times in a short period of time until the smart home performs the correct action. Therefore, the probability of users using non-standard vocabulary and requiring optimization is higher during this time period.

[0035] In one specific embodiment, the present invention detects the interaction records of each target intelligent control device and obtains user voice information that has more than three dialogues within one minute from the interaction records. This information is then analyzed and optimized to further avoid the situation where a small number of dialogues collected in a short period of time are all correct dialogues, reduce the workload of ineffective optimization, and further improve the pertinence and accuracy of dialogue optimization.

[0036] Step S104: Identify the user's true intent based on the user's voice information.

[0037] Step S105: Adjust the standard script and script response strategy of the target intelligent control device according to the user's true intention.

[0038] Specifically, after collecting user voice information, semantic analysis is performed on the user voice information to identify keywords and user intent, thereby determining why the target smart control device cannot correctly match the user intent, and further determining the reason for the low usage rate of the target smart control device. Then, based on the user's true intent, the standard script and script response strategy of the target smart control device are adjusted, improving the accuracy of the target smart control device in recognizing user voice and the accuracy of executing actions without the user's active feedback, thus improving the timeliness of smart home script optimization. In this embodiment, the specific implementation scheme for obtaining user intent through semantic analysis of user voice information can be executed through a pre-trained semantic analysis model. The pre-trained semantic analysis model can adopt common natural language processing techniques, which are existing technologies and will not be elaborated in this embodiment.

[0039] In some alternative implementations, step S102 includes:

[0040] Step a1: Obtain the base date.

[0041] Step a2: Count the number of devices remaining each day from the base date to the preset number of days. The number of devices remaining is the number of smart control devices that are active on both the base date and the count date. The count date is any date within the preset number of days.

[0042] Step a3: Determine the target date from the statistical dates where the number of devices retained is less than the preset threshold based on the number of devices retained each day.

[0043] Step a4: Detect smart control devices that are inactive within each target date and use the detected smart control devices as target smart control devices.

[0044] Specifically, in this embodiment, the number of devices remaining is calculated by detecting whether certain devices were used on previous dates and then reused on subsequent dates. This remaining number is then used to identify target smart control devices with low usage rates, thus improving the accuracy of target smart control device identification. The concepts involved in the calculation include:

[0045] Active: Active refers to the use of intelligent control devices;

[0046] The baseline date refers to the first date on which the intelligent control devices were active. The number of intelligent control devices used on the baseline date is used to determine whether the devices are retained on subsequent dates.

[0047] Statistical Date: The statistical date is a date within a preset number of days after the base date. The number of smart control devices used on the statistical date is used together with the number of smart control devices used on the base date to calculate the number of devices retained.

[0048] Device retention count: Device retention count refers to the number of intelligent control devices that are active on both the baseline date and the statistical date;

[0049] For example, suppose 200 smart control devices were active on the baseline date of August 1st. We would obtain the activity data for the following week, specifically the daily activity count from August 2nd to August 8th. If 250 devices were active on August 2nd, but only 116 of them were active on August 1st, then the device retention count for August 2nd would be 116. Similarly, if 230 devices were active on August 3rd, but only 111 of them were active on August 1st, then the device retention count for August 3rd would be 111. The same logic applies to other dates.

[0050] In the above manner, embodiments of the present invention determine the target date from the statistical dates where the number of device retentions is less than a preset threshold based on the number of device retentions on each day. The preset threshold can be customized according to user needs, and there are no special restrictions on the specific value. For example, if the preset threshold is set to 100 devices, and the number of devices retained from August 2nd to August 8th are 116, 111, 96, 95, 112, 88, and 91 respectively, then the dates with fewer than 100 are August 4th, 5th, 7th, and 8th. Therefore, August 4th, 5th, 7th, and 8th are the target dates. Finally, the system detects inactive smart control devices on each target date. That is, on the four days of August 4th, 5th, 7th, and 8th when there are fewer active devices, the system searches for specific smart control devices that have not been active. For example, it obtains information such as the IP information and MAC code of the smart control devices to identify them. The detected smart control devices are then identified as target smart control devices with low usage rates. This method has higher data accuracy and stability, a higher probability that the target smart control devices found will be abandoned by users, and a lower probability of misjudgment, thereby improving the accuracy of target smart control device identification.

[0051] In an optional implementation, step S104 includes:

[0052] Step b1: When the user's voice information indicates that the user is continuously controlling two or more smart home devices, the user's true intention is to control multiple devices in a coordinated manner.

[0053] Step b2: When the user's voice information indicates that the corresponding smart home device does not exist in the corresponding room, the user's true intention is to control the device according to the user's naming habits.

[0054] Step b3: When the user's voice information indicates that there is no corresponding smart home device in the current room but there is a corresponding smart home device in other rooms, the user's true intention is to control the device according to the device name.

[0055] Specifically, embodiments of the present invention provide three methods for automatically identifying a user's true intent based on user voice information. The first method involves reading user voice information from a target smart control device and identifying if the information indicates that the user is continuously controlling two or more smart home devices within a short period. For example... Figure 2 As shown, a MAC address is selected from the target smart control devices. If the user issues three or more commands within one minute, such as "Hmm", "Oh, turn off the lights", or "Close all curtains", the user's true intention is to turn off the lights first and then close the curtains, based on the preset semantic analysis model. Therefore, this embodiment considers the user's reason for abandoning the current smart control device to be that multiple steps are required to turn off multiple smart home devices one by one, making it inconvenient. Thus, for this scenario, this embodiment marks the user's true intention as "multi-device linkage control". Subsequent script optimization steps need to optimize the linkage control of the devices to improve the accuracy of script optimization and increase the utilization rate of the smart control device.

[0056] The second method involves reading the user's voice information for a target smart control device and discovering that this information indicates the absence of the corresponding smart home device in the room. For example... Figure 3 As shown, the user called out three times, but none of the commands correctly operated our device. It was discovered that the smart control device did not have names like "secondary bedroom," "living room," or "room," thus preventing the device from being controlled correctly. In this scenario, this embodiment of the invention marks the user's true intention as controlling the device according to their naming habits. Therefore, the subsequent script optimization steps need to optimize the room name of the device to improve the accuracy of the script optimization and increase the utilization rate of the smart control device.

[0057] The third method involves reading the user's voice information for a target smart control device and discovering that this information indicates the corresponding smart home device does not exist in the current room, but does exist in other rooms. For example... Figure 4 As shown, the user's first voice command was to close the curtains, but the smart control device responded that no device could be executed. This is because the smart control device defaults to executing devices in the current room, indicating that there are no curtains in the current room and no corresponding device can be found. Through the subsequent two commands, it was detected that the user's actual intention was to close the bedroom curtains, which is not the current room. Therefore, this embodiment marks this type of scenario as indicating that the user's true intention is to control the device according to its name. Consequently, subsequent voice command optimization steps need to optimize the automatic matching of device names to improve the accuracy of the voice command optimization and increase the utilization rate of the smart control device.

[0058] In some optional implementations, when the true intention of the user is multi-device linkage control, the above step S105 specifically includes:

[0059] Step c1: determining a plurality of target smart home devices to be controlled continuously from the user voice information;

[0060] Step c2: determining a first verbal command according to the first piece of voice information that includes the target smart home device and is received in the user voice information;

[0061] Step c3: setting linkage control instructions for the plurality of target smart home devices;

[0062] Step c4: binding the first verbal command and the linkage control instructions, and burning the binding result into a target smart control device.

[0063] Specifically, for a scenario where the multi-device linkage control function is not available, in the implementation of the present invention, a plurality of target smart home devices to be controlled continuously are first determined from the user voice information. For example, by using a pre-trained semantic detection model and word segmentation technology, the keywords "light" and "curtain" are determined from the user voice information, and then it is determined that the target smart home devices that the user wants to control in linkage in the current scenario are the "light" and the "curtain" respectively. After that, the first piece of voice information that includes the target smart home device in the user voice information is determined, for example, the first command "Oh turn off the light" in the example mentioned in the foregoing embodiment. This command is the first command that contains one target smart home device "light", so that the corresponding "turn off the light" is taken as the first verbal command, and the command that the user is accustomed to shouting first is generated in a customized manner.

[0064] After that, linkage control instructions for the plurality of target smart home devices are set, for example, the linkage control instructions for the "light" and the "curtain" are set, such that as long as the "light" among the "light" and the "curtain" is turned off, the "curtain" is also turned off in linkage. Finally, the server binds the extracted first verbal command and the linkage control instructions, and burns the binding result into the target smart control device through the network. In this way, when the user habitually shouts "turn off the light", the smart control device responds to the received first verbal command, can control the "light" and the "curtain" to be turned off together in linkage, improves the user experience, reduces user control operations, and significantly improves the accuracy and efficiency of verbal command optimization.

[0065] In some optional implementations, to further optimize the dialogue and make the control strategy simpler and the dialogue easier to remember, the server also generates recommended scenario dialogue based on the set linkage control commands. That is, it automatically generates dialogue suitable for the current scenario based on the scenario adapted to the current device linkage control. For example, if the linkage control commands are to turn off the lights and close the curtains, a pre-trained machine learning model can detect that the scenario closest to the current control strategy is a sleeping scenario, thus generating the recommended scenario dialogue "I want to sleep". The machine learning model used for semantic recognition and data matching is a relatively mature technology in the field of natural language processing, and the pre-training process of the model will not be described in detail in this embodiment. Afterwards, the server can send the recommended scenario dialogue to the smart control device. When the user uses the smart control device next time, the smart control device will play a voice message and / or display a screen prompting the user whether to set up the linkage control command according to the recommended scenario dialogue. If the user agrees to set it up, the recommended scenario dialogue and linkage control command will be bound together and saved in the smart control device. When the user says the recommended scenario dialogue (e.g., "I want to sleep"), the linkage control command will take effect (e.g., simultaneously control the lights to turn off and the curtains to close). This solution further improves the accuracy of dialogue optimization.

[0066] In some alternative implementations, when the user's true intention is to control the device according to their naming conventions, step S105 specifically includes:

[0067] Step d1: Extract room name information from user voice information;

[0068] Step d2: Determine the target smart home device to be controlled from the user's voice information;

[0069] Step d3: Determine the target name information from the standard room name and corresponding smart home device information stored in the target smart control device based on the target smart home device;

[0070] Step d4: Replace the target name information in the target smart control device with the room name information.

[0071] Specifically, in this embodiment, for scenarios where room names do not match, the server first extracts room name information from the user's voice information of a target smart control device. For example, if the user commands to open device 1 ("secondary bedroom"), device 2 ("living room"), and device 3 ("master bedroom"), the room names would be "secondary bedroom," "living room," and "master bedroom," respectively. Then, the server determines the target smart home device to be controlled from the user's voice information. For example, based on the user's commands, it detects that the target smart home devices the user wants to control are device 1, device 2, and device 3. Then, the target name information is determined from the standard room names and corresponding smart home device information stored in the target smart control device. For example, the standard room names stored in the target smart control device are Room 1, Room 2, Room 3, etc., and Device 1 is in Room 1, Device 2 is in Room 2, and Device 3 is in Room 3. The corresponding target name information is Room 1, Room 2, and Room 3. Thus, it is determined that the secondary bedroom corresponds to Room 1, the living room corresponds to Room 2, and the master bedroom corresponds to Room 3. Therefore, if the user wants to control the smart home correctly, the correct wording should be to say "Open Device 1 in Room 1", "Open Device 2 in Room 2", and "Open Device 3 in Room 3".

[0072] Since the aforementioned standard commands do not conform to user habits, this embodiment, after determining the correspondence, replaces the target name information in the target smart control device with room name information extracted from the user's voice information. This replaces the standard names Room 1, Room 2, and Room 3 stored in the smart control device with "Secondary Bedroom," "Living Room," and "Master Bedroom," respectively. After the replacement, the user can issue voice commands according to their usage habits, thereby accurately controlling smart home devices. This improves the accuracy of the optimized commands, enhances the user experience, and reduces the abandonment rate of smart control devices.

[0073] In some alternative implementations, when the user's true intention is to control the device by device name, step S105 includes:

[0074] Step e1: Determine the target voice information that successfully controlled the smart home device from the user's voice information.

[0075] Step e2: Analyze the target voice information to obtain the target smart home device controlled by the target voice information.

[0076] Step e3: Determine the second voice command based on the first voice message received from the user's voice information that contains the target smart home device.

[0077] Step e4: Associate the second voice command with the target smart home device and burn the association result into the target smart control device.

[0078] Specifically, in this embodiment, the server determines the target voice information that successfully controls the smart home device from the user's voice information. For example, if the user says "close the curtains" and "close the bedroom curtains," then "close the bedroom curtains" successfully controls the curtains, while "close the curtains" does not because there are no curtains in the room. Therefore, the command "close the bedroom curtains" is taken as the target voice information. Next, this target voice information is parsed to determine that the actual controlled smart home device is the curtains. Then, the first command containing this smart home device is found from all the user's voice messages, which in the example above corresponds to "close the curtains." Thus, this embodiment associates the command "close the curtains" as the second voice command with the aforementioned target smart home device "curtains." Finally, the server burns the association result into the target smart control device.

[0079] With this solution, when users give commands like "close the curtains" based on their own habits, which are often vague about the device's location, the smart control device can still determine that the bedroom curtains need to be closed based on the saved associations. This avoids situations where the device location cannot be matched correctly, improves the accuracy of the command optimization, and thus improves the accuracy of device control, enhances the user experience, and reduces the abandonment rate of smart control devices.

[0080] This embodiment also provides a smart home dialogue optimization device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0081] This embodiment provides a smart home dialogue optimization device, such as... Figure 5 As shown, it includes:

[0082] The authorization module 501 is used to obtain user authorization information sent by the intelligent control devices in each room. For details, please refer to the relevant description of step S101 in the above method embodiment, which will not be repeated here.

[0083] The device monitoring module 502 is used to identify target intelligent control devices with low usage rates in response to user authorization information. For details, please refer to the relevant description of step S102 in the above method embodiment, which will not be repeated here.

[0084] The voice information acquisition module 503 is used to acquire user voice information continuously received by each target intelligent control device within a preset time period. For details, please refer to the relevant description of step S103 in the above method embodiment, which will not be repeated here.

[0085] The cause identification module 504 is used to identify the user's true intent based on the user's voice information. For details, please refer to the relevant description of step S104 in the above method embodiment, which will not be repeated here.

[0086] The adjustment module 505 is used to adjust the standard script and script response strategy of the target intelligent control device according to the user's true intention. For details, please refer to the relevant description of step S105 in the above method embodiment, which will not be repeated here.

[0087] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0088] In this embodiment, the smart home dialogue optimization device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0089] This invention also provides a computer device having the above-described features. Figure 5 The smart home dialogue optimization device shown.

[0090] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 6 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take a processor 10 as an example.

[0091] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0092] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0093] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0094] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0095] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0096] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0097] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for optimizing smart home communication scripts, characterized in that, The method comprises: acquiring user authorization information sent by intelligent control devices in each room; identifying a target intelligent control device with a low usage rate in response to the user authorization information; acquiring user voice information continuously received by each of the target intelligent control devices within a preset time length; identifying the true user intention according to the user voice information; the identifying the true user intention according to the user voice information comprises: when the user voice information indicates that the user continuously controls two or more smart home devices, the true user intention is multi-device linkage control; when the user voice information indicates that there is no corresponding smart home device in the corresponding room, the true user intention is to control the device according to naming habits; when the user voice information indicates that there is no corresponding smart home device in the current room but a corresponding smart home device exists in other rooms, the true user intention is to control the device according to the device name; adjusting the standard speech and speech response strategy of the target intelligent control device according to the true user intention.

2. The method according to claim 1, characterized in that, The identifying a target intelligent control device with a low usage rate in response to the user authorization information comprises: acquiring a reference date; counting the number of retained devices each day from the reference date to after a preset number of days, where the number of retained devices is the number of intelligent control devices that are active on both the reference date and the statistical date, and the statistical date is any date within the preset number of days; determining a target date on which the number of retained devices is less than a preset threshold from the statistical dates according to the number of retained devices on each day; detecting intelligent control devices that are inactive within each of the target dates, and taking the detected intelligent control devices as the target intelligent control devices.

3. The method according to claim 1, characterized in that, The acquiring user voice information continuously received by each of the target intelligent control devices within a preset time length comprises: detecting interaction records of each of the target intelligent control devices, and acquiring the user voice information with more than three dialogues occurring within one minute from the interaction records.

4. The method according to claim 1, characterized in that, When the true user intention is multi-device linkage control, the adjusting the standard speech and speech response strategy of the target intelligent control device according to the true user intention comprises: determining a plurality of target smart home devices that are controlled continuously from the user voice information; determining a first speech command according to the first piece of voice information including the target smart home device received in the user voice information; setting a linkage control instruction for the plurality of target smart home devices; binding the first speech command and the linkage control instruction, and burning the binding result into the target intelligent control device.

5. The method according to claim 1, characterized in that, When the true user intention is to control the device according to naming habits, the adjusting the standard speech and speech response strategy of the target intelligent control device according to the true user intention comprises: extracting room address information from the user voice information; determining the target smart home device to be controlled from the user voice information; determining target name information from the correspondence information between standard room names and smart home devices stored by the target intelligent control device according to the target smart home device; Replace the target name information in the target intelligent control device with the room appellation information.

6. The method according to claim 1, characterized in that, When the true intention of the user is to control the device according to the device name, the adjusting the standard speech and speech response strategy of the target intelligent control device according to the true intention of the user includes: Determine the target voice information that successfully controls the smart home device from the user voice information; Parse the target voice information to obtain the target smart home device controlled by the target voice information; Determine a second speech command according to the first piece of voice information that includes the target smart home device and is received in the user voice information; Associate the second speech command with the target smart home device, and burn the association result into the target intelligent control device.

7. A smart home dialogue optimization device, characterized in that, The apparatus comprises: An authorization module, configured to acquire user authorization information sent by the intelligent control devices in each room; A device monitoring module, configured to identify a target intelligent control device with a low usage rate in response to the user authorization information; A voice information acquisition module, configured to acquire user voice information continuously received by each of the target intelligent control devices within a preset time length; An intention recognition module, configured to recognize the true intention of the user according to the user voice information; the recognizing the true intention of the user according to the user voice information includes: when the user voice information indicates that the user continuously controls two or more smart home devices, the true intention of the user is multi-device linkage control; when the user voice information indicates that the corresponding smart home device does not exist in the corresponding room, the true intention of the user is to control the device according to appellation habits; when the user voice information indicates that the corresponding smart home device does not exist in the current room but exists in other rooms, the true intention of the user is to control the device according to the device name; An adjustment module, configured to adjust the standard speech and speech response strategy of the target intelligent control device according to the true intention of the user.

8. A computer device, characterized in that, Comprising: A memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the computer instructions, so as to perform the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, Computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to perform the method according to any one of claims 1 to 6.

Images