Disclosure of Invention
The invention mainly aims to provide a household appliance control method, electronic equipment and a computer readable storage medium, and aims to solve the problems of poor classification effect, poor accuracy and efficiency and poor control accuracy of household appliances caused by adopting other general classification modes to classify texts in the field of household appliances at present.
In order to achieve the above object, the present invention provides a method for controlling a home appliance, comprising the steps of:
acquiring text data to be identified;
comparing the text data to be recognized with text data in a preset text database, and finding out text content and variable with the highest similarity to the text data to be recognized from the preset text database;
generating a classification recognition result of the text data to be recognized according to the text content with the highest similarity and the variable;
and controlling the household appliance based on the classification recognition result.
Optionally, the step of comparing the text data to be recognized with text data in a preset text database, and finding out the text content and the variable with the highest similarity to the text data to be recognized from the preset text database includes:
converting the text data to be recognized into text data corresponding to a statement format in a preset text database;
comparing the converted text data with the text data in a preset text database to obtain the similarity between the converted text data and the text data in the preset text database;
and finding out the text content and the variable with the highest similarity.
Optionally, the step of comparing the text data to be recognized with text data in a preset text database, and finding out the text content and the variable with the highest similarity to the text data to be recognized from the preset text database includes:
extracting feature data from the text data to be recognized;
comparing the text data to be identified with the text data content matched with the characteristic data in a preset text database;
and finding out the text content and the variable with the highest similarity with the text data to be recognized from the matched preset text data content.
Optionally, the step of comparing the text data to be recognized with the text data content matched with the feature data in a preset text database includes:
dividing the text data to be identified according to the service types according to the feature data;
and comparing the text data to be identified with the text data content matched with the characteristic data in a preset text database according to the service type.
Optionally, the controlling the home appliance based on the classification recognition result includes:
sending the classification recognition result to a third party terminal so that the third party terminal can generate a control instruction according to the classification recognition result to control the household appliance; or,
and generating a control instruction according to the classification recognition result, and sending the control instruction to the third party terminal to control the household appliance.
Optionally, the step of acquiring text data to be recognized includes:
and when the received data to be recognized is data except for the text, converting the received data to be recognized into text data serving as the text data to be recognized.
Optionally, after the step of generating the classification recognition result of the text data to be recognized according to the text content with the highest similarity and the variable, the method further includes:
and when the received data to be recognized is data except for the text, converting the classification recognition result into data with the same format as the received data to be recognized, and outputting the converted classification recognition result.
Optionally, before the step of comparing the text data to be recognized with text data in a preset text database, and finding out text content and a variable with the highest similarity to the text data to be recognized from the preset text database, the method further includes:
preprocessing the text data to be recognized, extracting characteristic words, segmenting the text data to be recognized, and removing stop words from the segmented text data to be recognized.
In addition, to achieve the above object, the present invention also provides an electronic device including: the household appliance control method comprises a memory, a processor and a household appliance control program which is stored on the memory and can run on the processor, wherein the household appliance control program realizes the household appliance control method when being executed by the processor.
In addition, to achieve the above object, the present invention also provides a computer-readable storage medium having a home appliance control program stored thereon, the home appliance control program implementing the home appliance control method as described above when executed by a processor.
According to the method, the preset text database is built in the text to be recognized, the text database is divided into the text content and the variable, the text to be recognized and the text content and the variable in the preset text database are recognized and matched aiming at the special variable of the household appliance, the text recognition in the field of household appliances is met, the accuracy and the efficiency of classification recognition are improved, and then the household appliances are accurately controlled.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The main solution of the embodiment of the invention is as follows: acquiring text data to be identified; comparing the text data to be recognized with text data in a preset text database, and finding out text content and variable with the highest similarity to the text data to be recognized from the preset text database; generating a classification recognition result of the text data to be recognized according to the text content with the highest similarity and the variable; and controlling the household appliance based on the classification recognition result.
The problem of poor control accuracy of household appliances is caused by poor classification effect, poor accuracy and poor efficiency caused by adopting other general classification modes to classify texts in the field of household appliances at present. The invention provides a solution, a preset text database is established in a text to be recognized, the text database is divided into text contents and variables, and the text contents and the variables in the text to be recognized and the preset text database are recognized, so that the special variables of household appliances are recognized and matched, the text recognition in the field of household appliances is met, the accuracy and the efficiency of classification recognition are improved, and further the household appliances are accurately controlled.
As shown in fig. 1, fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present invention.
The electronic equipment in the embodiment of the invention can be equipment which can be controlled by an air conditioner, a fan, a refrigerator and the like, can also be control equipment such as a PC, a smart phone, a tablet personal computer or a portable computer, or equipment such as a server or a home gateway.
As shown in fig. 1, the electronic device may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Optionally, the electronic device may further include a camera, RF (Radio Frequency) circuitry, sensors, audio circuitry, a WiFi module, an anemometer, and so forth. Such as image sensors, infrared sensors, and other sensors. Specifically, the image sensor or the infrared sensor can detect the position of a user in the space acted by the air conditioner, and the rotating speed of the indoor fan of the air conditioner is controlled through the position. The wind speed measuring instrument is used for measuring the wind speed of the position where a user is located, and the wind speeds of different positions are different. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally, three axes), detect the magnitude and direction of gravity when the motion sensor is stationary, and can be used for applications of recognizing the posture of electronic equipment (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer and tapping) and the like; of course, the electronic device may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, a temperature sensor, and a holman sensor, which are not described herein again.
Those skilled in the art will appreciate that the terminal structure shown in fig. 1 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a home appliance control application program.
In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a backend server and performing data communication with the backend server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to call the appliance control application stored in the memory 1005 and perform the following operations:
acquiring text data to be identified;
comparing the text data to be recognized with text data in a preset text database, and finding out text content and variable with the highest similarity to the text data to be recognized from the preset text database;
generating a classification recognition result of the text data to be recognized according to the text content with the highest similarity and the variable; and controlling the household appliance based on the classification recognition result.
Further, the processor 1001 may be configured to invoke a home appliance control application stored in the memory 1005 and perform the following operations:
converting the text data to be recognized into text data corresponding to a statement format in a preset text database;
comparing the converted text data with the text data in a preset text database to obtain the similarity between the converted text data and the text data in the preset text database;
and finding out the text content and the variable with the highest similarity.
Further, the processor 1001 may be configured to invoke a home appliance control application stored in the memory 1005 and perform the following operations:
extracting feature data from the text data to be recognized;
comparing the text data to be identified with the text data content matched with the characteristic data in a preset text database;
and finding out the text content and the variable with the highest similarity with the text data to be recognized from the matched preset text data content.
Further, the processor 1001 may be configured to invoke a home appliance control application stored in the memory 1005 and perform the following operations:
dividing the text data to be identified according to the service types according to the feature data;
and comparing the text data to be identified with the text data content matched with the characteristic data in a preset text database according to the service type.
Further, the processor 1001 may be configured to invoke a home appliance control application stored in the memory 1005 and perform the following operations:
sending the classification recognition result to a third party terminal so that the third party terminal can generate a control instruction according to the classification recognition result to control the household appliance; or,
and generating a control instruction according to the classification recognition result, and sending the control instruction to the third party terminal to control the household appliance.
Further, the processor 1001 may be configured to invoke a home appliance control application stored in the memory 1005 and perform the following operations:
and when the received data to be recognized is data except for the text, converting the received data to be recognized into text data serving as the text data to be recognized.
Further, after the step of generating the classification recognition result of the text data to be recognized according to the text content and the variable with the highest similarity, the processor 1001 may be configured to invoke a home appliance control application stored in the memory 1005, and perform the following operations:
and when the received data to be recognized is data except for the text, converting the classification recognition result into data with the same format as the received data to be recognized, and outputting the converted classification recognition result.
Further, before the step of comparing the text data to be recognized with the text data in the preset text database and finding out the text content and the variable with the highest similarity to the text data to be recognized from the preset text database, the processor 1001 may be configured to invoke the home appliance control application program stored in the memory 1005, and perform the following operations:
preprocessing the text data to be recognized, extracting characteristic words, segmenting the text data to be recognized, and removing stop words from the segmented text data to be recognized.
Referring to fig. 2, a first embodiment of the present invention provides a home appliance control method including:
step S10, acquiring text data to be recognized;
in this embodiment, when the APP of the home appliance is opened, or when the APP enters the operation interface of the home appliance through a browser, or when the home appliance is operated by other means, information is input, where the input information includes, but is not limited to, text information, voice information, image information, remote control code information, or the like.
The input information is information for controlling the household appliance by a user, and when the input information is information of other input types except text information, namely when the received data to be recognized is data except text, the received data to be recognized is converted into text data serving as the text data to be recognized. For example, voice information is converted into text data, or image data or video data is converted into text data or the like.
When the input information is in a text format, directly acquiring text data to be identified; and when the input information is in other formats (except the text format), converting the input information into text data, and acquiring the converted text data to be recognized.
In an embodiment of the present invention, the input information may be input by phone or text message (input by phone or text message or other input methods without an input box at long distance or short distance), rather than by the input interface alone.
Step S20, comparing the text data to be recognized with the text data in a preset text database, and finding out the text content and the variable with the highest similarity with the text data to be recognized from the preset text database;
and a text database is arranged in advance, and the preset text database comprises identification rules of text data in the field of household appliances and special division of certain words. Specifically, the preset text database includes: the method comprises the steps of arranging common sentence patterns and variable slots of certain voice, wherein the common sentence patterns and the variable slots of certain voice are required to be arranged, such as air conditioner temperature control, helping people adjust to 26 ℃, helping people adjust to 2 ℃ higher, and good heat, and the like, the intention is designated as temperature control, meanwhile, the variable slots are set as temperature, the unit is centigrade, the arranged sentence patterns are written into a set semantic format, a text database is formed according to the sentence patterns written into the set semantic format, the intention comprises the intention of each sentence and the variable slots of the intention, the intention is household appliance control, the variable slots are temperature control, frequency control or wind speed control, and the like. After the text data to be recognized is obtained, the text data to be recognized is compared with the text data in a preset text database, and the text content and the variable with the highest similarity to the text data to be recognized are found out from the preset text database.
In order to improve the accuracy of text data classification, in an embodiment of the present invention, before comparing text data to be recognized with a preset text database, the text data to be recognized is processed to remove interference, and the process of processing the text data to be recognized is as follows: preprocessing the text data to be recognized, extracting characteristic words, segmenting the text data to be recognized, and removing stop words from the segmented text data to be recognized. The processing process is a noise-removing process, interference is eliminated, subsequent classification and identification are more accurate, and the processing process can be realized by extracting characteristic words, segmenting words and taking out stop words through the existing preprocessing, and is not repeated one by one.
In order to better classify the text data to be recognized, referring to fig. 3, the step of comparing the text data to be recognized with the text data in a preset text database, and finding out the text content and the variable with the highest similarity to the text data to be recognized from the preset text database includes:
step S21, converting the text data to be recognized into text data corresponding to the sentence format in a preset text database;
step S22, comparing the converted text data with the text data in the preset text database to obtain the similarity between the converted text data and the text data in the preset text database;
step S23, the text content and the variable with the highest similarity are found out.
The method comprises the steps that a preset text database has a statement format, and after text data to be recognized are obtained, the text data to be recognized are converted into text data corresponding to the statement format in the preset text database; the comparison with a preset text database is convenient, the comparison effect is improved, and the classification and identification efficiency is further improved. And matching the similarity between the text data to be identified and a preset text database in the comparison process, and finding out the text content and the variable with the highest similarity.
To further improve the efficiency and accuracy of classification identification, the following can be dealt with:
referring to fig. 4, the step of 1) comparing the text data to be recognized with the text data in a preset text database, and finding out the text content and the variable with the highest similarity to the text data to be recognized from the preset text database includes:
step S24, extracting characteristic data from the text data to be recognized;
step S25, comparing the text data to be recognized with the text data content matched with the characteristic data in a preset text database;
step S26, finding out the text content and the variable with the highest similarity to the text data to be recognized from the matched preset text data content.
When comparison is carried out, feature data are extracted firstly, the feature data are set in advance, the feature data are divided according to user requirements or common habits, a preset text database is divided into a plurality of sub-text databases according to the feature data, after the feature data are extracted, the sub-text databases matched with the feature data are compared with the sub-text databases in the preset text database instead of other sub-text databases, time is saved, and comparison efficiency is improved.
Referring to fig. 5, 2) the step of comparing the text data to be recognized with the text data content matched with the feature data in the preset text database includes:
step S27, dividing the text data to be recognized according to the service type according to the feature data;
and step S28, comparing the text data to be recognized with the text data content matched with the characteristic data in a preset text database according to the service type.
Setting a service type, identifying the service type, such as a control type, a short message service type or a weather type, according to the characteristic data extraction, dividing a preset text database into sub-text databases of the service type according to the service type, and when comparing, firstly, matching the corresponding sub-text databases according to the service type corresponding to the text data to be identified and the service type.
In other embodiments of the present invention, the service type division and the feature data can be matched with the sub-text database separately, and are not combined together to match the sub-text database. And matching the sub-text database by extracting characteristic data or service types (identification or keyword extraction and the like) independently, and comparing the text content with the highest similarity and the variable. It should be understood that only two ways of improving the recognition accuracy and efficiency are described above, and other recognition ways within the scope of the present invention are also included in the present invention, and are not described in detail herein.
Step S30, generating a classification recognition result of the text data to be recognized according to the text content with the highest similarity and the variable;
and after comparing the text content with the highest similarity with the variable, generating a classification recognition result of the text data to be recognized according to the text content with the highest similarity and the variable. For example, a classification recognition result is obtained in which the temperature is controlled and the temperature is raised by 2 degrees. Or inquiring the classification recognition results of weather, weather conditions at any place and any time, and the like.
After the classification recognition result is obtained, the classification result is output according to different classifications, for example, a voice reply or a short message reply or the like, or is directly output on an APP or a browser interface.
And when the classification recognition result is output, if the received data to be recognized is data except for the text, converting the classification recognition result into data with the same format as the received data to be recognized, and outputting the converted classification recognition result. The input and output formats are the same, and the operation is more convenient.
And step S40, controlling the household appliance based on the classification recognition result.
And after the identification result is obtained or the identification result is output, controlling the household appliance based on the classification identification result.
Specifically, referring to fig. 6, the controlling the home appliance based on the classification recognition result includes:
and step S41, sending the classification recognition result to a third party terminal so that the third party terminal can generate a control instruction according to the classification recognition result to control the corresponding equipment to operate.
Alternatively, referring to fig. 7, the controlling the home appliance based on the classification recognition result includes:
and step S42, generating a control instruction according to the classification recognition result, and sending the control instruction to the third-party terminal to control the corresponding equipment to operate.
When the variable is control of the home appliance, for example, air conditioner temperature control or dehumidifier control is performed. And locally generating a control instruction according to the classification recognition result, or returning the classification recognition result to a third-party terminal, and generating the control instruction according to the classification recognition result at the third-party terminal. The generation of the control instruction according to the classification recognition result includes but is not limited to: and controlling the temperature, increasing the temperature by 2 degrees, generating a control command for increasing the temperature of the air conditioner by 2 degrees by the air conditioner, and generating a specific control command according to a classification recognition result. The control instruction is selected to be generated at the local terminal side or the third-party terminal side according to the setting of the user, and of course, the control instruction can be generated at both the local terminal side and the third-party terminal side, and the control instructions generated by the local terminal side and the third-party terminal side are compared to obtain the final control instruction from the comparison result to control the running of the household appliance. For example, the final control instruction with the highest weight value is selected, or the final control instruction is generated by combining the control instructions of the two according to the weight coefficient, and there are many other ways to combine the control instructions of the two or select one of the control instructions to control the home appliance, which is not described herein again. The third party terminal can be a control device or a server or a household appliance, and the local part is a classification identification side. The control instruction is generated at the local or third-party terminal, so that the method is more flexible and is convenient for the user to operate. It is understood that the text recognition is not limited to the control of the home appliance during the application in the home appliance field, but also can be used in the aspects of after-sale consultation of the home appliance, recommendation of the home appliance and the like. Specifically, different identifications are made through different input information, the input information is not limited to controlling the household appliance, but also can be used for obtaining the information of the household appliance, obtaining the operation information of the household appliance, inquiring information (weather, product encyclopedia, telephone short messages, after-sale consultation, smiling words and the like), storing the intention of each text and the variable slot of the intention in a preset text database, and correspondingly converting the household appliance control into the intention and the variable slot of the weather, the product encyclopedia and the after-sale consultation.
In the embodiment, the preset text database is established in the text to be recognized, the text database is divided into the text content and the variable, the recognition and the matching are performed on the special variable of the household appliance through the recognition of the text content and the variable in the text to be recognized and the preset text database, the text recognition in the field of household appliances is met, the accuracy and the efficiency of classification recognition are improved, and the household appliance is accurately controlled.
The present invention also provides an electronic device, including: the household appliance control method comprises a memory, a processor and a household appliance control program which is stored on the memory and can run on the processor, wherein the household appliance control program realizes the household appliance control method according to the embodiment when being executed by the processor.
In the embodiment, the preset text database is built in the text to be recognized, the text database is divided into the text content and the variable, the recognition of the text content and the variable in the text to be recognized and the preset text database is performed, the special variable of the household appliance is recognized and matched, the text recognition in the field of household appliances is met, the accuracy and the efficiency of classification recognition are improved, and then the household appliances are accurately controlled.
Furthermore, an embodiment of the present invention further provides a computer-readable storage medium, where a home appliance control program is stored on the computer-readable storage medium, and when executed by the processor, the home appliance control program implements the following operations:
acquiring text data to be identified;
comparing the text data to be recognized with text data in a preset text database, and finding out text content and variable with the highest similarity to the text data to be recognized from the preset text database;
generating a classification recognition result of the text data to be recognized according to the text content with the highest similarity and the variable;
and controlling the household appliance based on the classification recognition result.
Further, the home appliance control program when executed by the processor performs the following operations:
converting the text data to be recognized into text data corresponding to a statement format in a preset text database;
comparing the converted text data with the text data in a preset text database to obtain the similarity between the converted text data and the text data in the preset text database;
and finding out the text content and the variable with the highest similarity.
Further, the home appliance control program when executed by the processor performs the following operations:
extracting feature data from the text data to be recognized;
comparing the text data to be identified with the text data content matched with the characteristic data in a preset text database;
and finding out the text content and the variable with the highest similarity with the text data to be recognized from the matched preset text data content.
Further, the home appliance control program when executed by the processor performs the following operations:
dividing the text data to be identified according to the service types according to the feature data;
and comparing the text data to be identified with the text data content matched with the characteristic data in a preset text database according to the service type.
Further, the home appliance control program when executed by the processor performs the following operations:
sending the classification recognition result to a third party terminal so that the third party terminal can generate a control instruction according to the classification recognition result to control the household appliance; or,
and generating a control instruction according to the classification recognition result, and sending the control instruction to the third party terminal to control the household appliance.
Further, the home appliance control program when executed by the processor performs the following operations:
and when the received data to be recognized is data except for the text, converting the received data to be recognized into text data serving as the text data to be recognized.
Further, after the step of generating the classification recognition result of the text data to be recognized according to the text content and the variable with the highest similarity, the home appliance control program, when executed by the processor, implements the following operations:
and when the received data to be recognized is data except for the text, converting the classification recognition result into data with the same format as the received data to be recognized, and outputting the converted classification recognition result.
Further, before the step of comparing the text data to be recognized with the text data in a preset text database and finding out the text content and the variable with the highest similarity to the text data to be recognized from the preset text database, the home appliance control program is executed by the processor to implement the following operations:
preprocessing the text data to be recognized, extracting characteristic words, segmenting the text data to be recognized, and removing stop words from the segmented text data to be recognized.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.