Air conditioner control adjustment method and system, and computer device

Abstract

The application discloses a kind of vehicle air conditioner control adjustment methods, comprising: obtaining the playing data of vehicle multimedia device, the playing data includes one or more combinations of playing audio, playing video or playing image;Respectively to the playing data is handled to generate the sentiment weight value of playing data;According to the sentiment weight value of playing data, the semantic weight value corresponding to the semantic sentiment of vehicle multimedia semantic sentiment is generated;According to the preset weight value control rule and semantic weight value, determine the current semantic emotion mode of vehicle multimedia, and according to the semantic weight value, control the air conditioning temperature value and air volume in vehicle.The application also discloses a kind of vehicle air conditioner control adjustment system and computer equipment.By using the application, the air conditioning temperature and air volume of vehicle can be controlled according to the semantic emotion of vehicle multimedia, so that the passengers in vehicle can be immersed in different temperature changes along with the emotional semantics of multimedia playing.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle air-conditioning control, and in particular to a vehicle air-conditioning control and adjustment method and system, and a computer device. Background Art

[0002] With the improvement of living standards and the development of intelligent technology, people's demand for entertainment enjoyment is getting higher and higher. As an important means of transportation for people, cars occupy a lot of people's time. Therefore, people are eager to enjoy a higher-dimensional emotional experience while driving.

[0003] Prior art methods for automatically adjusting a car's temperature primarily involve detecting the remaining charge in the car's power battery and the actual temperature inside the car. When the actual temperature exceeds a first preset threshold, a first adjustment temperature is determined based on the actual temperature, the remaining charge, and a first correspondence. The air conditioner is then adjusted until the actual temperature reaches the first adjustment temperature. While this method can maintain a comfortable temperature inside the car, providing a better experience for drivers and passengers, its temperature control is solely based on the remaining charge and the actual temperature inside the car, without considering emotional factors. This prevents passengers from engaging in a more nuanced emotional experience, and therefore fails to meet new consumer needs. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method, system and computer equipment for controlling and adjusting vehicle air conditioning, so that passengers in the vehicle can integrate into different temperature changes along with the emotional semantics of multimedia playback.

[0005] In order to solve the above technical problems, the present invention provides a method for controlling and adjusting vehicle air conditioning, including: obtaining playback data of a vehicle-mounted multimedia device, the playback data including one or more combinations of playing audio, playing video or playing images; processing the playback data respectively to generate emotional weight values ​​of the playback data; generating semantic weight values ​​corresponding to the semantic emotions of the vehicle-mounted multimedia according to the emotional weight values ​​of the playback data; determining the current semantic emotional mode of the vehicle-mounted multimedia according to preset weight value control rules and semantic weight values, and controlling the air conditioning temperature value and air output volume in the vehicle according to the semantic weight values.

[0006] As an improvement to the above scheme, when the playback data includes playback audio, the step of processing the playback data to generate an emotional weight value of the playback data includes: performing semantic recognition on the playback audio through semantic recognition technology, and converting the playback audio into text information; performing feature recognition on the text information through a preset emotional vocabulary library, and extracting emotional text related to emotions in the text information; calculating an average text weight value based on a preset first weight value and the emotional text; and using the average text weight value as the emotional weight value of the playback audio.

[0007] As an improvement to the above scheme, the steps of performing feature recognition on the text information through a preset emotional vocabulary library and extracting emotional text related to emotions in the text information include: segmenting the text information to generate multiple paragraphs of text information; segmenting each paragraph of text information to generate multiple sentences of text information; segmenting each sentence of text information to generate multiple word information; inputting each word information into the emotional vocabulary library for feature comparison, and when the word information is consistent with the target word in the emotional vocabulary library, the word information is used as emotional text.

[0008] As an improvement to the above scheme, when the playback data includes playback video, the step of processing the playback data to generate an emotional weight value of the playback data includes: performing image frame segmentation processing on the playback video in units of frames to generate multiple image frames; performing feature recognition on each image frame respectively to extract the image features of the image frame; performing feature recognition on the image features through a preset feature emotion library to extract emotional features related to emotions in the image features; calculating the emotional weight value of the image frame based on a preset second weight value and the emotional features; calculating the average of the emotional weight values ​​of all image frames to generate an average video weight value; and using the average video weight value as the emotional weight value of the playback video.

[0009] As an improvement to the above scheme, when the playback data includes playback images, the step of processing the playback data to generate an emotional weight value of the playback data includes: performing feature recognition on each playback image respectively, and extracting the image features of the playback image; performing feature recognition on the image features through a preset feature emotion library, and extracting emotional features related to emotions in the image features; calculating the emotional weight value of the playback image based on a preset third weight value and the emotional features; calculating the average of the emotional weight values ​​of all playback images to generate an image average weight value; and using the image average weight value as the emotional weight value of the playback image.

[0010] As an improvement of the above scheme, the step of generating the semantic weight value corresponding to the semantic emotion of the in-vehicle multimedia based on the emotional weight value of the playback data includes: calculating the weight sum of the emotional weight values ​​of the playback data, or calculating the weight sum of the emotional weight values ​​of the playback data according to a preset ratio; calculating the average value of the weight sum to generate the weight value corresponding to the semantic emotion of the in-vehicle multimedia.

[0011] As an improvement of the above scheme, the semantic emotion mode includes spring mode, summer mode, autumn mode and winter mode. The corresponding weight values ​​of the summer mode, autumn mode, spring mode and winter mode in the preset weight value control rules decrease successively, and the corresponding air-conditioning temperature values ​​of the summer mode, autumn mode, spring mode and winter mode decrease successively.

[0012] Correspondingly, the present invention also provides a vehicle-mounted air-conditioning control and adjustment system, including: an acquisition module for acquiring playback data of a vehicle-mounted multimedia device, wherein the playback data includes one or more combinations of playing audio, playing video or playing images; an emotion weight module for processing the playback data separately to generate emotion weight values ​​of the playback data; a semantic weight module for generating semantic weight values ​​corresponding to the semantic emotions of the vehicle-mounted multimedia based on the emotion weight values ​​of the playback data; a control module for determining the current semantic emotion mode of the vehicle-mounted multimedia based on preset weight value control rules and semantic weight values, and controlling the air-conditioning temperature value and air output volume in the vehicle based on the semantic weight values.

[0013] As an improvement of the above-mentioned scheme, the emotion weight module includes an audio submodule, and the audio submodule includes: a semantic recognition unit, which is used to perform semantic recognition on the playback audio through semantic recognition technology and convert the playback audio into text information; a text recognition unit, which is used to perform feature recognition on the text information through a preset emotion vocabulary library and extract emotion-related emotion text in the text information; a first weight calculation unit, which is used to calculate the average text weight value based on the preset first weight value and the emotion text, and use the average text weight value as the emotion weight value of the playback audio.

[0014] As an improvement of the above scheme, the emotion weight module includes a video recording submodule, which includes: an image frame segmentation unit, which is used to perform image frame segmentation processing on the playback video in units of frames to generate multiple image frames; an image frame recognition unit, which is used to perform feature recognition on each image frame respectively to extract the image features of the image frame; a frame feature recognition unit, which is used to perform feature recognition on the image features through a preset feature emotion library to extract emotion-related emotion features from the image features; a second weight calculation unit, which is used to calculate the emotion weight value of the image frame based on a preset second weight value and the emotion feature; a video recording calculation unit, which is used to average the emotion weight values ​​of all image frames to generate a video recording average weight value, and use the video recording average weight value as the emotion weight value of the playback video.

[0015] As an improvement of the above scheme, the emotion weight module includes an image submodule, and the image submodule includes: a playback image recognition unit, which is used to perform feature recognition on each playback image respectively and extract the image features of the playback image; an image feature recognition unit, which is used to perform feature recognition on the image features through a preset feature emotion library and extract emotion features related to emotions in the image features; a third weight calculation unit, which is used to calculate the emotion weight value of the playback image based on a preset third weight value and the emotion features; an image calculation unit, which is used to average the emotion weight values ​​of all playback images, generate an image average weight value, and use the image average weight value as the emotion weight value of the playback image.

[0016] Correspondingly, the present invention further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0017] The implementation of the present invention has the following beneficial effects:

[0018] The present invention can acquire the playback data played on the in-vehicle multimedia device in the car, and process the audio, video and image separately to extract their corresponding emotional weight values. Then, the semantic emotional mode of the current in-vehicle multimedia is determined based on the emotional weight values ​​of the three. The vehicle's air conditioning temperature and air volume are controlled according to the determined semantic emotional mode, so that the passengers in the car can integrate into the different temperature changes along with the emotional semantics of the multimedia playback, achieving a higher-dimensional emotional experience.

[0019] Furthermore, the present invention also sets four different emotional modes: spring, summer, autumn and winter, to simulate the four different seasonal feelings of spring, summer, autumn and winter, which is more suitable for practical applications;

[0020] In addition, the present invention also combines word technology, image frame segmentation technology and image processing technology to process in-vehicle multimedia content, thereby achieving accurate extraction of emotional features and making it easier to determine semantic emotions. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flow chart of an embodiment of a vehicle air conditioning control and adjustment method of the present invention;

[0022] Figure 2 is a flowchart of an embodiment of processing the playback data to generate an emotion weight value of the playback data when the playback data includes playback audio in the present invention;

[0023] Figure 3 is a flowchart of an embodiment of processing the playback data to generate an emotion weight value of the playback data when the playback data includes playback video in the present invention;

[0024] Figure 4 is a flow chart of an embodiment of processing the playback data to generate an emotion weight value of the playback data when the playback data includes a playback image in the present invention;

[0025] Figure 5 It is a structural schematic diagram of the vehicle air-conditioning control and adjustment system of the present invention;

[0026] Figure 6 It is a structural diagram of the emotion weight module in the vehicle air-conditioning control and regulation system of the present invention. DETAILED DESCRIPTION

[0027] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be described in further detail below with reference to the accompanying drawings.

[0028] See also Figure 1 , Figure 1 The flowchart of an embodiment of the vehicle air conditioning control and adjustment method of the present invention is shown, which includes:

[0029] S101, obtaining playback data of an in-vehicle multimedia device.

[0030] The playback data includes one or more combinations of playing audio, playing video or playing images.

[0031] S102: Process the playback data respectively to generate emotion weight values ​​of the playback data.

[0032] It should be noted that the audio playback, video playback or image playback can be processed separately. Specifically:

[0033] When the playback data only contains playback audio / playback video / playback image, processing the playback audio / playback video / playback image to generate an emotion weight value of the playback audio / playback video / playback image;

[0034] When the playback data contains playback audio and playback video, playback video and playback image, or playback audio and playback image at the same time, the playback audio and playback video, playback video and playback image, or playback audio and playback image are processed respectively to generate an emotion weight value of the playback audio and an emotion weight value of the playback video, an emotion weight value of the playback video and an emotion weight value of the playback image, or an emotion weight value of the playback audio and an emotion weight value of the playback image;

[0035] When the playback data contains playback images, playback videos and playback images at the same time, the playback images, playback videos and playback images are processed respectively to generate the emotional weight value of the playback audio, the emotional weight value of the playback video and the emotional weight value of the playback image.

[0036] S103 , generating a semantic weight value corresponding to the semantic emotion of the in-vehicle multimedia according to the emotion weight value of the playback data.

[0037] Furthermore, the emotional weight values ​​of the playback data generated in step S102 may be averaged to calculate the semantic weight value corresponding to the semantic emotion of the in-vehicle multimedia. Specifically, step S103 includes:

[0038] (1) Calculating the weighted sum of the emotional weight values ​​of the playback data, or calculating the weighted sum of the emotional weight values ​​of the playback data according to a preset ratio.

[0039] It should be noted that the preset ratio can be transformed or changed according to actual application requirements, and the present invention does not limit it.

[0040] (2) Calculate the average value of the weighted sum to generate the weight value corresponding to the semantic emotion of the in-vehicle multimedia.

[0041] For example, when the playback data contains playback images, playback videos and playback images at the same time, the emotional weight value of the playback audio, the emotional weight value of the playback video and the emotional weight value of the playback image are averaged, and the semantic weight value corresponding to the semantic emotion of the in-vehicle multimedia can be calculated.

[0042] S104, determining the current semantic emotion mode of the vehicle multimedia according to the preset weight value control rules and the semantic weight value, and controlling the temperature value and air volume of the air conditioner in the vehicle according to the semantic weight value.

[0043] Therefore, the present invention can obtain the playback data played on the in-vehicle multimedia device in the car, and process the audio, video and image separately, extract their corresponding emotional weight values, and then determine the semantic emotional pattern of the current in-vehicle multimedia based on the emotional weight values ​​of the three, and control the air-conditioning temperature and air volume of the vehicle according to the determined semantic emotional pattern.

[0044] Specifically, the semantic emotion mode includes a spring mode, a summer mode, an autumn mode and a winter mode.

[0045] The corresponding weight values ​​of the summer mode, autumn mode, spring mode, and winter mode in the preset weight value control rule decrease in sequence. For example, if the weight values ​​are divided into four levels, where the first level is 0-2, the second level is 3-5, the third level is 6-8, and the fourth level is 9-10, when the semantic weight value is 1, it means that the current semantic emotion mode of the in-vehicle multimedia is winter mode, and when the semantic weight value is 7, it means that the current semantic emotion mode of the in-vehicle multimedia is autumn mode.

[0046] Correspondingly, the corresponding air conditioning temperature values ​​of the summer mode, autumn mode, spring mode and winter mode decrease in sequence. That is, when the current semantic emotion mode of the in-vehicle multimedia is the summer mode, the air conditioning temperature value is increased to bring the passengers in the car into the feeling of summer.

[0047] As can be seen from the above, the present invention addresses the current lack of technical solutions for in-vehicle temperature control based on emotional factors in automotive applications, and provides a method for controlling and adjusting in-vehicle air conditioning. Based on the emotional semantics of the playback data output by the in-vehicle multimedia device, the present invention controls the temperature and air volume of the in-vehicle air conditioning to simulate the four different seasonal sensations of spring, summer, autumn, and winter. This allows passengers to experience the different temperature changes as the emotional semantics of the multimedia playback unfolds, achieving a higher-dimensional emotional experience.

[0048] See also Figure 2 , Figure 2 It is shown that when the playback data includes playback audio, the step of processing the playback data to generate the emotion weight value of the playback data includes:

[0049] S201, performing semantic recognition on the played audio through semantic recognition technology, and converting the played audio into text information.

[0050] S202: performing feature recognition on the text information using a preset emotional word library to extract emotional words related to emotions from the text information.

[0051] In the present invention, the semantic emotion patterns include spring, summer, autumn, and winter patterns. Accordingly, when calculating the emotion weight values, the word features in the emotion word library can also be divided into four patterns: spring, summer, autumn, and winter. The emotion word library refers to a database containing emotion words.

[0052] Specifically, step S202 includes:

[0053] (1) Segmenting the text information to generate multiple segments of text information;

[0054] (2) Separately process each paragraph of text information into sentences to generate multiple sentences of text information;

[0055] (3) Segment each sentence of text information to generate multiple word information;

[0056] (4) Each word information is input into the emotional word library for feature comparison. When the word information is consistent with the target word in the emotional word library, the word information is used as emotional text.

[0057] After all the segmented word information is compared, all the extracted emotional texts are obtained.

[0058] S203: Calculate an average text weight value based on a preset first weight value and the emotional text.

[0059] S204: Using the average text weight value as the emotion weight value of the played audio.

[0060] For example, when only the song "My Passion is Like a Fire" is played on the in-vehicle multimedia device, it means that the played audio is "My Passion is Like a Fire"; at this time, it can be recognized that the emotional text in the currently played audio contains: passion, fire; then, according to the preset first weight value (such as: passion 8, fire 10), the average weight value of the text is calculated (such as: (8+10) / 2=9), so that the emotional weight value of the audio played by the in-vehicle multimedia this time can be calculated as 9; therefore, the vehicle will determine the semantic weight value as 9 based on the emotional weight value, and actively cooperate with the driver to change the temperature and air volume in the car.

[0061] See also Figure 3 , Figure 3 It is shown that when the playback data includes playback video, the step of processing the playback data to generate the emotion weight value of the playback data includes:

[0062] S301 , performing image frame segmentation processing on the playback video in units of frames to generate a plurality of image frames.

[0063] S302 , performing feature recognition on each image frame to extract image features of the image frame.

[0064] S303: performing feature recognition on the image features through a preset feature emotion library, and extracting emotion-related emotion features from the image features.

[0065] In the present invention, the semantic emotion patterns include spring, summer, autumn, and winter patterns. Accordingly, when calculating the emotion weight values, the image features in the characteristic emotion library can also be divided into four patterns: spring, summer, autumn, and winter. The characteristic emotion library refers to a database containing emotion features.

[0066] S304: Calculate the emotion weight value of the image frame according to the preset second weight value and the emotion feature.

[0067] S305: Calculate the average value of the emotion weight values ​​of all image frames to generate an average video weight value.

[0068] S306: Using the average weight value of the videos as the emotional weight value for playing the videos.

[0069] After the calculation of the emotion weight values ​​of all the image frames is completed, the emotion weight values ​​of all the image frames are averaged, and the average value is used as the emotion weight value of the video playback.

[0070] See also Figure 4 , Figure 4 It is shown that when the playback data includes a playback image, the step of processing the playback data to generate an emotion weight value of the playback data includes:

[0071] S401 , performing feature recognition on each playback image to extract image features of the playback image.

[0072] S402: performing feature recognition on image features through a preset feature emotion library, and extracting emotion-related emotion features from the image features.

[0073] In the present invention, the semantic emotion patterns include spring, summer, autumn, and winter patterns. Accordingly, when calculating the emotion weight values, the image features in the characteristic emotion library can also be divided into four patterns: spring, summer, autumn, and winter. The characteristic emotion library refers to a database containing emotion features.

[0074] S403: Calculate the emotion weight value of the played image according to the preset third weight value and the emotion feature.

[0075] S404: Calculate the average of the emotion weight values ​​of all played images to generate an average image weight value.

[0076] S405: Using the average image weight value as the emotion weight value of the played image.

[0077] After the calculation of the emotion weight values ​​of all images is completed, the emotion weight values ​​of all images are averaged, and the average value is used as the emotion weight value of the played image.

[0078] comprehensive Figure 2-Figure 4 It can be seen that the processing of playing audio, playing video or playing images all contains corresponding preset weight values ​​(such as the first weight value, the second weight value and the third weight value). Each weight value can be transformed and modified according to actual application requirements. It can be the same or different, and it is highly flexible.

[0079] From the above, it can be seen that the present invention combines word technology, image frame segmentation technology and image processing technology to process the in-vehicle multimedia content, thereby realizing the extraction of emotional features; at the same time, the present invention sets four different emotional modes of spring, summer, autumn and winter, and controls the temperature and air volume in the car according to the playback content of the in-vehicle multimedia to simulate the four different seasonal feelings of spring, summer, autumn and winter, so that the passengers in the car can integrate into the different temperature changes with the emotional semantics of the multimedia playback, thereby realizing a higher-dimensional emotional experience.

[0080] See also Figure 5 , Figure 5 The specific structure of the vehicle air conditioning control and adjustment system 100 of the present invention is shown, which includes:

[0081] The acquisition module 1 is used to acquire the playback data of the vehicle-mounted multimedia device, wherein the playback data includes one or more combinations of audio playback, video playback, or image playback.

[0082] The emotion weight module 2 is used to process the playback data respectively to generate emotion weight values ​​of the playback data.

[0083] The semantic weight module 3 is used to generate a semantic weight value corresponding to the semantic emotion of the in-vehicle multimedia based on the emotional weight value of the playback data. Furthermore, the emotional weight value of the playback data generated in the emotional weight module 2 can be averaged to calculate the semantic weight value corresponding to the semantic emotion of the in-vehicle multimedia. Specifically, the weight sum of the emotional weight values ​​of the playback data can be calculated, or the weight sum of the emotional weight values ​​of the playback data can be calculated according to a preset ratio, and then the weight sum can be averaged to generate the weight value corresponding to the semantic emotion of the in-vehicle multimedia. Among them, the preset ratio can be transformed or changed according to actual application requirements, and the present invention is not limited thereto.

[0084] The control module 4 is used to determine the current semantic emotion mode of the vehicle multimedia according to the preset weight value control rules and semantic weight values, and control the air conditioning temperature and air volume in the vehicle according to the semantic weight values.

[0085] Specifically, the semantic emotion mode includes a spring mode, a summer mode, an autumn mode, and a winter mode. In the preset weight value control rule, the corresponding weight values ​​of the summer mode, autumn mode, spring mode, and winter mode decrease in sequence, and the corresponding air conditioning temperature values ​​of the summer mode, autumn mode, spring mode, and winter mode decrease in sequence. In other words, when the current semantic emotion mode of the in-vehicle multimedia is the summer mode, the air conditioning temperature value is increased to bring the passengers in the vehicle into a summer feeling.

[0086] Therefore, the present invention can acquire the playback data played on the in-vehicle multimedia device in the car through the acquisition module 1, and process the audio, video and image respectively through the emotion weight module 2 to extract their corresponding emotion weight values, and then the semantic weight module 3 determines the semantic weight value of the current in-vehicle multimedia according to the emotion weight values ​​of the three, and then the control module 4 determines the semantic emotion mode of the current in-vehicle multimedia, and controls the air-conditioning temperature and air volume of the vehicle according to the determined semantic emotion mode.

[0087] like Figure 6 As shown, the emotion weight module 2 includes an audio submodule 21, a video submodule 22 and an image submodule 23. It should be noted that when the playback data contains playback audio, the audio submodule 21 processes the playback audio to generate an emotion weight value of the playback audio; when the playback data contains playback video, the video submodule 22 processes the playback video to generate an emotion weight value of the playback video; when the playback data contains playback image, the image submodule 23 processes the playback image to generate an emotion weight value of the playback image. Specifically:

[0088] The audio submodule 21 includes:

[0089] The semantic recognition unit 211 is configured to perform semantic recognition on the playback audio using a semantic recognition technology, and convert the playback audio into text information.

[0090] The text recognition unit 212 is used to perform feature recognition on the text information through a preset emotional word library, and extract emotional text related to emotions in the text information. In the present invention, the semantic emotional mode includes spring mode, summer mode, autumn mode and winter mode. Accordingly, when calculating the emotional weight value, the word features in the emotional word library can also be divided into four modes of spring, summer, autumn and winter, wherein the emotional word library refers to a database containing emotional words. Specifically, the text recognition unit 212 first segments the text information to generate multiple paragraphs of text information; then, it separately processes each paragraph of text information into sentences to generate multiple sentences of text information; then, it separately processes each sentence of text information to generate multiple word information; finally, each word information is input into the emotional word library for feature comparison. When the word information is consistent with the target word in the emotional word library, the word information is used as emotional text.

[0091] The first weight calculation unit 213 is used to calculate an average text weight value according to a preset first weight value and the emotional text, and use the average text weight value as the emotional weight value of the played audio.

[0092] In addition, the video recording submodule 22 includes:

[0093] The image frame segmentation unit 221 is configured to perform image frame segmentation processing on the playback video in units of frames to generate a plurality of image frames.

[0094] The image frame recognition unit 222 is configured to perform feature recognition on each image frame and extract image features of the image frame.

[0095] The frame feature recognition unit 223 is configured to perform feature recognition on the image features using a preset feature emotion library, and extract emotion-related emotional features from the image features. In the present invention, the semantic emotion patterns include spring, summer, autumn, and winter patterns. Accordingly, when calculating emotion weights, the image features in the feature emotion library can also be divided into four patterns: spring, summer, autumn, and winter. The feature emotion library refers to a database containing emotional features.

[0096] The second weight calculation unit 224 is configured to calculate the emotion weight value of the image frame according to a preset second weight value and the emotion feature.

[0097] The video calculation unit 225 is used to calculate the average value of the emotion weight values ​​of all image frames to generate a video average weight value, and use the video average weight value as the emotion weight value of the played video.

[0098] Accordingly, the image submodule 23 includes:

[0099] The playback image recognition unit 231 is configured to perform feature recognition on each playback image and extract image features of the playback image.

[0100] Image feature recognition unit 232 is configured to perform feature recognition on the image features using a preset feature emotion library, and extract emotion-related emotional features from the image features. In the present invention, the semantic emotion patterns include spring, summer, autumn, and winter patterns. Accordingly, when calculating emotion weights, the image features in the feature emotion library can also be divided into four patterns: spring, summer, autumn, and winter. The feature emotion library refers to a database containing emotional features.

[0101] The third weight calculation unit 233 is configured to calculate the emotion weight value of the playback image according to a preset third weight value and the emotion feature.

[0102] The image calculation unit 234 is configured to calculate an average value of the emotion weight values ​​of all the played images to generate an image average weight value, and use the image average weight value as the emotion weight value of the played image.

[0103] It should be noted that the first weight calculation unit 213, the second weight calculation unit 224 and the third weight calculation unit 233 all contain their own corresponding preset weight values ​​(such as the first weight value, the second weight value and the third weight value). Each weight value can be transformed and modified according to actual application requirements. It can be the same or different, and has strong flexibility.

[0104] From the above, it can be seen that the present invention controls the temperature and air volume of the air conditioner in the car according to the emotional semantics of the playback data output by the in-vehicle multimedia device to simulate the four different seasonal feelings of spring, summer, autumn and winter, so that the passengers in the car can integrate into the different temperature changes with the emotional semantics of the multimedia playback, thereby achieving a higher-dimensional emotional experience.

[0105] Correspondingly, the present invention also discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein the processor implements the steps of the above-mentioned vehicle air conditioning control and adjustment method when executing the computer program.

[0106] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A vehicle air conditioning control and adjustment method, characterized in that: include: Acquiring playback data of an in-vehicle multimedia device, wherein the playback data includes one or more combinations of audio playback, video playback, or image playback; Processing the playback data respectively to generate emotion weight values ​​of the playback data; Generating a semantic weight value corresponding to the semantic emotion of the in-vehicle multimedia according to the emotional weight value of the playback data; Determine the current semantic emotion mode of the vehicle multimedia according to the preset weight value control rules and semantic weight values, and control the temperature value and air volume of the air conditioner in the vehicle according to the semantic weight values; Generating a semantic weight value corresponding to the semantic emotion of the in-vehicle multimedia according to the emotion weight value of the playback data includes: Calculating the weighted sum of the emotion weight values ​​of the playback data, or calculating the weighted sum of the emotion weight values ​​of the playback data according to a preset ratio; An average value is calculated for the weight sum to generate a semantic weight value corresponding to the semantic emotion of the in-vehicle multimedia.

2. The vehicle air conditioning control and adjustment method according to claim 1, characterized in that: When the playback data includes playback audio, the step of processing the playback data to generate an emotion weight value of the playback data includes: Perform semantic recognition on the played audio using semantic recognition technology, and convert the played audio into text information; Performing feature recognition on the text information using a preset emotional word library to extract emotional words related to emotions in the text information; Calculate the average weight value of the text according to the preset first weight value and the emotional text; The average text weight value is used as the emotional weight value of the played audio.

3. The vehicle air conditioning control and adjustment method according to claim 2, characterized in that: The step of performing feature recognition on the text information using a preset emotional word library to extract emotional words related to emotions in the text information includes: Segmenting the text information to generate multiple segments of text information; Separately process each paragraph of text information into sentences to generate multiple sentences of text information; Segment each sentence of text information to generate multiple word information; Each word information is input into the emotional word library for feature comparison. When the word information is consistent with the target word in the emotional word library, the word information is used as emotional text.

4. The vehicle air conditioning control and adjustment method according to claim 1, wherein: When the playback data includes playback video, the step of processing the playback data to generate the emotion weight value of the playback data includes: Performing image frame segmentation processing on the playback video in units of frames to generate multiple image frames; Performing feature recognition on each image frame respectively to extract image features of the image frame; Performing feature recognition on the image features using a preset feature emotion library to extract emotion-related emotion features from the image features; Calculating an emotional weight value of the image frame according to a preset second weight value and the emotional feature; Calculate the average of the emotional weight values ​​of all image frames to generate the average weight value of the video; The average weight value of the videos is used as the emotional weight value of the played videos.

5. The vehicle air conditioning control and adjustment method according to claim 1, characterized in that: When the playback data includes a playback image, the step of processing the playback data to generate an emotion weight value of the playback data includes: Performing feature recognition on each playback image to extract image features of the playback image; Performing feature recognition on the image features using a preset feature emotion library to extract emotion-related emotion features from the image features; Calculating an emotional weight value of the played image according to a preset third weight value and the emotional feature; Calculate the average of the emotional weight values ​​of all played images to generate the average image weight value; The average image weight value is used as the emotional weight value of the played image.

6. The vehicle air conditioning control and adjustment method according to any one of claims 1 or 5, characterized in that: The semantic emotion mode includes spring mode, summer mode, autumn mode and winter mode. The semantic weight values ​​corresponding to the summer mode, autumn mode, spring mode and winter mode in the preset weight value control rules decrease in sequence, and the air-conditioning temperature values ​​corresponding to the summer mode, autumn mode, spring mode and winter mode decrease in sequence.

7. A vehicle air conditioning control and adjustment system, characterized in that: include: An acquisition module, configured to acquire playback data of an in-vehicle multimedia device, wherein the playback data includes one or more combinations of audio playback, video playback, or image playback; An emotion weight module, configured to process the playback data respectively to generate emotion weight values ​​of the playback data; A semantic weight module, configured to generate a semantic weight value corresponding to the semantic emotion of the in-vehicle multimedia according to the emotional weight value of the playback data; A control module, configured to determine the current semantic emotion mode of the vehicle multimedia according to a preset weight value control rule and a semantic weight value, and to control the temperature value and air volume of the air conditioner in the vehicle according to the semantic weight value; The semantic weight module is specifically used to: Calculating the weighted sum of the emotion weight values ​​of the playback data, or calculating the weighted sum of the emotion weight values ​​of the playback data according to a preset ratio; An average value is calculated for the weight sum to generate a semantic weight value corresponding to the semantic emotion of the in-vehicle multimedia.

8. The vehicle air conditioning control and adjustment system according to claim 7, characterized in that: The emotion weight module includes one or more of an audio submodule, a video submodule, and an image submodule. The audio submodule includes: A semantic recognition unit, configured to perform semantic recognition on the played audio using a semantic recognition technology, and convert the played audio into text information; A text recognition unit, configured to perform feature recognition on the text information using a preset emotional word library, and extract emotional words related to emotions from the text information; A first weight calculation unit is used to calculate an average text weight value according to a preset first weight value and the emotional text, and use the average text weight value as the emotional weight value of the played audio; The video recording submodule includes: An image frame segmentation unit, configured to perform image frame segmentation processing on the playback video in units of frames to generate a plurality of image frames; An image frame recognition unit, configured to perform feature recognition on each image frame and extract image features of the image frame; A frame feature recognition unit, configured to perform feature recognition on the image features using a preset feature emotion library, and extract emotion-related emotion features from the image features; A second weight calculation unit, configured to calculate an emotion weight value of the image frame according to a preset second weight value and the emotion feature; A video calculation unit, configured to calculate an average of the emotion weight values ​​of all image frames to generate an average video weight value, and use the average video weight value as the emotion weight value of the played video; The image submodule includes: A playback image recognition unit, configured to perform feature recognition on each playback image and extract image features of the playback image; An image feature recognition unit, configured to perform feature recognition on the image features using a preset feature emotion library, and extract emotion-related emotion features from the image features; a third weight calculation unit, configured to calculate an emotional weight value of the playback image according to a preset third weight value and the emotional feature; The image calculation unit is used to calculate the average value of the emotion weight values ​​of all the played images to generate an image average weight value, and use the image average weight value as the emotion weight value of the played image.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

Images