Description:FIELD OF THE INVENTION
This invention relates to NLP and Sentiment Analysis-based Recommendation System for Victims of Domestic Violence.
BACKGROUND OF THE INVENTION
Millions of individuals, mostly women, from different cultural and economic backgrounds are profoundly affected by domestic violence, which is a global issue. The problem is widespread and takes many forms such as physical, sexual, emotional, psychological and financial abuse that inflict painful and lasting effects on the victims. Despite efforts by governments, NGOs and international organisations such as UN towards dealing with this menace; domestic violence is still a challenge due to its intricate nature. One of the key challenges faced by those facing abuse is the lack of easily accessible personalized support services. Fear stigma or practical issues prevent many victims from learning about what help they can get; others know about them but cannot access them. Furthermore, existing structures often do not have the capability to respond immediately to individual victim needs in a nuanced way. As such victims may suffer for long periods before they eventually die or become depressed eventually committing suicide.
The invention "NLP AND SENTIMENT ANALYSIS-BASED RECOMMENDATION SYSTEM FOR VICTIMS OF DOMESTIC VIOLENCE" utilize the power of cutting edge technology to provide an all-inclusive and personalized means of support. The technique involves complex natural language processing techniques and sentiment analysis algorithms that are used to interpret and examine victim’s stories. The system utilizes textual data to extract emotional as well as situational cues hence it can accurately gauge the severity of danger facing the victim. The approach also uses IoT devices like wearable safety gadgets, smart sensors among others for improved real-time monitoring and response functions besides text analyses. Those wearable gadgets track down the position of victims, monitor body behaviour changes such as heart rates, blood pressure for instance and send instant messages to select contacts or local authorities whenever there is a threat/attack. This on-time action ability helps in minimizing the intensity of an attack thus ensuring life safety. Moreover, the system fills an important gap in research regarding current technologies used for domestic violence intervention. It emphasizes that privacy must be maintained at all times with regard to confidential information at stake. It has a recommendation system which is a source of information on legal aid, safety planning tools as well as emotional support materials for survivors based on their different situations. Therefore, it empowers victims by allowing them to make informed choices and be proactive towards their own recovery and security. The "NLP and Sentiment Analysis-based Recommendation System for Victims of Domestic Violence" is an important step forward in the struggle against domestic violence. It bridges the gap between existing resources and the peculiar needs of victims, providing personalized assistance that is accessible and effective. This creates room not only for immediate crisis management but also long-term well-being of victims thereby aligning with global goals of gender equality, peace, justice, and strong institutions.
US9438731B2 A computer aided prioritization (CAP) system may receive, from the emergency event reporter device, an emergency event including a priority selected from a set of event priorities and a type of event selected from a set of event types associated with the selected event priority; determine, based on the emergency event and without querying the emergency event reporter device for additional information, whether the emergency event indicates a higher priority emergency event to be handled by a computer aided dispatch (CAD) system or a lower priority emergency event to be handled automatically by a computer aided event module (CAEM); and selectively route the emergency event report to at least one of the CAD system and the CAEM according to the determination.
RESEARCH GAP: Tailored Recommendations: The recommendation module uses a comprehensive knowledge base to provide customized advice, as well as resources based on the actual situation of detected distress. It guarantees victims get the right kind of support.
US11151318B2 Embodiments include computer-implemented methods and systems for detecting undesirable and potentially harmful online behavior. The embodiments described and claimed could also be applied to detecting any other type of online behavior to be detected, but the descriptions focuses on detecting online violence. More particularly, the embodiments disclosed relate to detecting online violence using symbolic methods of natural language processing (NLP) that utilize and govern the usage of: 1) syntactic parser for analyzing grammatical context of the input text data, 2) unsupervised learning methods for improving selected aspects of the system and adjusting the system to new data sources and guidelines, and 3) statistical classifiers for resolving specific well-defined sub-tasks, in which statistical approaches surpass the symbolic methods.
RESEARCH GAP: Privacy and Security: The concern about privacy and security have been addressed in designing this kind of a system. Data is processed locally in the device with only necessary data being sent to cloud services for further analysis. In return it minimizes chances of exposing data to wrong hands while keeping personal information confidentially safe for user.
US11308332B1 Systems, methods, and computer-readable media are disclosed for systems and methods for intelligent content rating determination. Example methods include determining presence of a first feature in a first frame of a video using an object recognition algorithm, determining presence of a second feature in an audio file associated with the video using an audio processing algorithm, and determining presence of a third feature in a text file associated with the video using a natural language processing algorithm. Certain embodiments may include generating a predicted content rating for the video using a machine learning model, where the predicted content rating is based at least in part on the first feature, the second feature, and the third feature, and using feedback data for the predicted content rating to retrain the machine learning model.
KR101051246B1 A technique is provided for detecting whether consumer abuse has occurred in an electronic device. According to this technique, a system is provided for detecting the occurrence of a consumer abuse event and storing a record of that event. In one embodiment, the system provides one or more sensors coupled to abuse detection circuitry for detecting the occurrence of abuse events. The system may further provide a memory, and when an abuse event is detected, the abuse detection circuitry may store a record of the abuse event in the memory. The system may determine whether an abuse event has occurred in the electronic device by a diagnostic device accessing the memory and analyzing the abuse event record.
RESEARCH GAP: Automated emergency alerts: When there is detected distress, the GSM module integrated into it sends automated alert messages to pre-set contacts or authorities
None of the prior art indicate above either alone or in combination with one another disclose what the present invention has disclosed. This invention relates to NLP and Sentiment Analysis-based Recommendation System for Victims of Domestic Violence.
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
The integration of different hardware components and software algorithms will form a cohesive and robust system architecture for the proposed "NLP and Sentiment Analysis Based Recommendation System for Victims of Domestic Violence." The system’s central processing unit is expected to be Raspberry Pi which will manage and synchronize the various sensors and peripherals, locally analyze data as well as facilitate connection with cloud solutions for further scrutiny. A neural compute stick boosting the computational capabilities of the Raspberry Pi will be included to handle complex machine learning models that execute faster hence making audio and video inputs’ processing more efficient.
Apart from the neural compute stick and a Raspberry Pi, a high-definition camera will be installed into this system in order to capture visual information about what is going on around it. This camera should be put strategically to cover significant areas, which are equipped with modern gesture-recognizing as well as face-detection software vital in identifying distress or violence signs. An audio device containing microphone would be used to record conversations happening within their surroundings including background noises. Such kinds of sounds may then be subjected to advanced NLP (Natural Language Processing) methods together with sentiment analysis so that abusive speeches or any signs pointing out to someone’s stress can easily identified. To ensure continuous operation, it will be necessary to integrate a power monitor that looks after the Raspberry Pi and other components’ power supply so as to keep the system working all the time. It may also be important to include a GPS module for tracking the location of the device which can be very crucial in emergency cases where location data is needed for prompt assistance. Additionally, there could be an integration of GSM module that enables sending alert messages by the system to predefined contacts or authorities whenever a distress signal has been detected with an aim of ensuring quick response. For efficient analysis of collected data, several sophisticated algorithms and models will be employed by this system. The main algorithm will use NLP techniques in order to process and understand textual and spoken inputs from victims. These techniques consist of tokenization, part-of-speech tagging, named entity recognition, and dependency parsing used for breaking down language used by victims into comprehendible forms. Sentiment analysis will also have a crucial role in assessing emotional content of data utilizing models such as Bidirectional Encoder Representations from Transformers (BERT), which allow high accuracy sentiment detection. BERT will be preferred because it can put words in the sentence’s context, so it understands the subtle language typically found in domestic violence scenarios. Convolutional neural networks (CNN) and recurrent neural networks (RNN) will be used alongside BERT for this analysis. For CNNs, they are useful for image and video handling which aids in identifying various physical gestures that could indicate danger and facial expressions reflecting fear. RNNs especially long short-term memory (LSTM) are used to process sequential audio data which helps detect abusive language patterns over time. The training of these models involves publicly available datasets about domestic violence, sentiment analysis and speech recognition as well as some proprietary data obtained through partnerships with relevant organizations and support groups. The first stage of the processing pipeline is data acquisition, whereby visual information is captured by a camera while audio information is continuously recorded by a microphone. The Raspberry Pi is then able to process this raw data on real-time basis using its neural compute stick. However, CNNs study the video feed to find out whether there is any physical indication of distress like aggressive gestures or frightened facial expressions. Concomitantly, NLP techniques are applied on the audio data.
The sentiment analysis module then sends the transcribed text from audio data and detected gestures from visual data for BERT model to analyze how emotional a conversation is and if it comprises distress signals. This will signal the presence of any kind of suffering, prompting the recommendation module to access knowledge base containing legal resources, support services as well as emergency contacts. Based on the given scenario, this will therefore lead to a number of responses which are tailored in nature. Such may include immediate steps towards ensuring safety, contact information for local support services or even legal advice that is specific to victim’s situation. These outputs are provided through a user-friendly interface displayed on a connected device like a tablet or smartphone. Further still, this system can send real-time alerts to predefined emergency contacts or authorities via GSM module thereby providing timely assistance and assuring help is coming. Comprehensively, thus overall architecture inclusive of high-tech algorithms in conjunction with advanced hardware elements desires creating a strong system that reacts immediately when acted upon. This will allow it not only to find cases of domestic violence, but also to provide survivors with recommendations, resources, and support which are appropriate and timely by using AI and machine learning in a meaningful way. The system is equipped with diverse hardware and software components that ensure its continuous monitoring capability and prompt assistance, which eventually enhance the security of those suffering from domestic violence.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
FIGURE 1: Flow diagram of the complete system
FIGURE 2: Process flow
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
A NLP and sentiment analysis based recommendation system for victims of domestic violence comprises a camera (101), a microprocessor (102), an audio device (103), a microphone (104), a Natural language processing model (105), a power supply (106), a GPS module (107), a GSM Module (108), a neural computer stick (109), wherein the camera is installed into this system in order to capture visual information about what is going on around it.
In another embodiment the microprocessor is able to process the raw data on real-time basis using its neural compute stick (109).
In another embodiment the audio device containing microphone would be used to record conversations happening within their surroundings including background noises; Such kinds of sounds may then be subjected to advanced NLP (Natural Language Processing) methods together with sentiment analysis so that abusive speeches or any signs pointing out to someone’s stress can easily identified.
In another embodiment the GPS module is used for tracking the location of the device which can be very crucial in emergency cases where location data is needed for prompt assistance.
In another embodiment the GSM module enables sending alert messages by the system to predefined contacts or authorities whenever a distress signal has been detected with an aim of ensuring quick response.
The integration of different hardware components and software algorithms will form a cohesive and robust system architecture for the proposed "NLP and Sentiment Analysis Based Recommendation System for Victims of Domestic Violence." The system’s central processing unit is expected to be Raspberry Pi which will manage and synchronize the various sensors and peripherals, locally analyze data as well as facilitate connection with cloud solutions for further scrutiny. A neural compute stick boosting the computational capabilities of the Raspberry Pi will be included to handle complex machine learning models that execute faster hence making audio and video inputs’ processing more efficient.
Apart from the neural compute stick and a Raspberry Pi, a high-definition camera will be installed into this system in order to capture visual information about what is going on around it. This camera should be put strategically to cover significant areas, which are equipped with modern gesture-recognizing as well as face-detection software vital in identifying distress or violence signs. An audio device containing microphone would be used to record conversations happening within their surroundings including background noises. Such kinds of sounds may then be subjected to advanced NLP (Natural Language Processing) methods together with sentiment analysis so that abusive speeches or any signs pointing out to someone’s stress can easily identified. To ensure continuous operation, it will be necessary to integrate a power monitor that looks after the Raspberry Pi and other components’ power supply so as to keep the system working all the time. It may also be important to include a GPS module for tracking the location of the device which can be very crucial in emergency cases where location data is needed for prompt assistance. Additionally, there could be an integration of GSM module that enables sending alert messages by the system to predefined contacts or authorities whenever a distress signal has been detected with an aim of ensuring quick response. For efficient analysis of collected data, several sophisticated algorithms and models will be employed by this system. The main algorithm will use NLP techniques in order to process and understand textual and spoken inputs from victims. These techniques consist of tokenization, part-of-speech tagging, named entity recognition, and dependency parsing used for breaking down language used by victims into comprehendible forms. Sentiment analysis will also have a crucial role in assessing emotional content of data utilizing models such as Bidirectional Encoder Representations from Transformers (BERT), which allow high accuracy sentiment detection. BERT will be preferred because it can put words in the sentence’s context, so it understands the subtle language typically found in domestic violence scenarios. Convolutional neural networks (CNN) and recurrent neural networks (RNN) will be used alongside BERT for this analysis. For CNNs, they are useful for image and video handling which aids in identifying various physical gestures that could indicate danger and facial expressions reflecting fear. RNNs especially long short-term memory (LSTM) are used to process sequential audio data which helps detect abusive language patterns over time. The training of these models involves publicly available datasets about domestic violence, sentiment analysis and speech recognition as well as some proprietary data obtained through partnerships with relevant organizations and support groups. The first stage of the processing pipeline is data acquisition, whereby visual information is captured by a camera while audio information is continuously recorded by a microphone. The Raspberry Pi is then able to process this raw data on real-time basis using its neural compute stick. However, CNNs study the video feed to find out whether there is any physical indication of distress like aggressive gestures or frightened facial expressions. Concomitantly, NLP techniques are applied on the audio data.
The sentiment analysis module then sends the transcribed text from audio data and detected gestures from visual data for BERT model to analyze how emotional a conversation is and if it comprises distress signals. This will signal the presence of any kind of suffering, prompting the recommendation module to access knowledge base containing legal resources, support services as well as emergency contacts. Based on the given scenario, this will therefore lead to a number of responses which are tailored in nature. Such may include immediate steps towards ensuring safety, contact information for local support services or even legal advice that is specific to victim’s situation. These outputs are provided through a user-friendly interface displayed on a connected device like a tablet or smartphone. Further still, this system can send real-time alerts to predefined emergency contacts or authorities via GSM module thereby providing timely assistance and assuring help is coming. Comprehensively, thus overall architecture inclusive of high-tech algorithms in conjunction with advanced hardware elements desires creating a strong system that reacts immediately when acted upon. This will allow it not only to find cases of domestic violence, but also to provide survivors with recommendations, resources, and support which are appropriate and timely by using AI and machine learning in a meaningful way. The system is equipped with diverse hardware and software components that ensure its continuous monitoring capability and prompt assistance, which eventually enhance the security of those suffering from domestic violence.
A NLP and sentiment analysis based recommendation system for victims of domestic violence comprises a camera (101), a microprocessor (102), an audio device (103), a microphone (104), a Natural language processing model (105), a power supply (106), a GPS module (107), a GSM Module (108), a neural computer stick (109), wherein the camera is installed into this system in order to capture visual information about what is going on around it. The microprocessor is able to process the raw data on real-time basis using its neural compute stick (109).
In another embodiment the audio device containing microphone would be used to record conversations happening within their surroundings including background noises; said sounds are subjected to advanced NLP (Natural Language Processing) methods together with sentiment analysis so that abusive speeches or any signs pointing out to someone’s stress can easily identified.
In another embodiment the GPS module is used for tracking the location of the device which can be very crucial in emergency cases where location data is needed for prompt assistance.
In another embodiment the GSM module enables sending alert messages by the system to predefined contacts or authorities whenever a distress signal has been detected with an aim of ensuring quick response.
In another embodiment the Raspberry Pi is configured to process real-time audio and video data from the camera and microphone; and the neural compute stick is used to accelerate the processing of machine learning models for NLP and sentiment analysis.
In another embodiment the camera is equipped with gesture recognition and face detection software; and the audio device is configured to record background noises and ambient sounds.
In another embodiment the power monitor is configured to automatically switch to a backup power source in case of a power outage; and the GPS module is configured to transmit location data to a predefined emergency contact or authority.
In another embodiment the GSM module is configured to send alert messages based on distress signals detected by the system; and the NLP algorithms include tokenization, part-of-speech tagging, named entity recognition, and dependency parsing.
In another embodiment the sentiment analysis module uses the BERT model for high-accuracy sentiment detection; and the system is configured to provide tailored recommendations and resources to victims of domestic violence based on their specific situation.
ADVANTAGES OF THE INVENTION
1. LIVE MONITORING AND DETECTION: The system uses HD cameras and microphones that enable non-stop real-time monitoring of the surroundings. This allows for immediate detection of any danger signs or violence, thus helping to prevent unfortunate occurrences.
2. ADVANCED CALCULATING CAPACITY: With a neural compute stick and Raspberry Pi, this system can handle complex machine learning models faster. Thus, it can process audio and visual data quickly by maintaining high degrees of accuracy while dealing with potential threats.
3. THOROUGH DATA ANALYSIS: It entails use of advanced algorithms such as CNNs in visual data and RNNs in audio data to ensure complete analysis on different types of inputs. Such a multimodal approach enhances accuracy and increases reliability in distress detection.
4. SENTIMENT ANALYSIS THAT TAKES THE CONTEXT INTO ACCOUNT : By using BERT for sentiment analysis, the system is better able to understand the context within which words are used in a sentence, making it highly effective at detecting nuanced language commonly associated with domestic violence cases. This results in more accurate identification of distress signals.
5. USER-FRIENDLY INTERFACE: The system has a user-friendly interface that presents recommendations and resources to the victim. This interface is intuitive, allowing users to obtain help and support whenever needed.
6. CONTINUOUS OPERATION: A power monitor included in it ensures that the system will still be available for use even when there are fluctuations in power supply. This permits uninterrupted monitoring and protection.
, Claims:1. A NLP and sentiment analysis based recommendation system for victims of domestic violence comprises a camera (101), a microprocessor (102), an audio device (103), a microphone (104), a Natural language processing model (105), a power supply (106), a GPS module (107), a GSM Module (108), a neural computer stick (109), wherein the camera is installed into this system in order to capture visual information about what is going on around it;
wherein the microprocessor is able to process the raw data on real-time basis using its neural compute stick (109).
2. The system as claimed in claim 1, wherein the audio device containing microphone would be used to record conversations happening within their surroundings including background noises; said sounds are subjected to advanced NLP (Natural Language Processing) methods together with sentiment analysis so that abusive speeches or any signs pointing out to someone’s stress can easily identified.
3. The system as claimed in claim 1, wherein the GPS module is used for tracking the location of the device which can be very crucial in emergency cases where location data is needed for prompt assistance.
4. The system as claimed in claim 1, wherein the GSM module enables sending alert messages by the system to predefined contacts or authorities whenever a distress signal has been detected with an aim of ensuring quick response.
5. The system as claimed in claim 1, wherein the Raspberry Pi is configured to process real-time audio and video data from the camera and microphone; and the neural compute stick is used to accelerate the processing of machine learning models for NLP and sentiment analysis.
6. The system as claimed in claim 1, wherein the camera is equipped with gesture recognition and face detection software; and the audio device is configured to record background noises and ambient sounds.
7. The system as claimed in claim 1, wherein the power monitor is configured to automatically switch to a backup power source in case of a power outage; and the GPS module is configured to transmit location data to a predefined emergency contact or authority.
8. The system as claimed in claim 1, wherein the GSM module is configured to send alert messages based on distress signals detected by the system; and the NLP algorithms include tokenization, part-of-speech tagging, named entity recognition, and dependency parsing.
9. The system as claimed in claim 1, wherein the sentiment analysis module uses the BERT model for high-accuracy sentiment detection; and the system is configured to provide tailored recommendations and resources to victims of domestic violence based on their specific situation.