This article explores the applications of NLP in business, accelerating theCV analysis, improving recruitment and marketing throughanalysis of customer reviews, and optimizing customer service with Chatbots. It contributes to the medical research, strengthens the fight against COVID-19, improves the safety at work, guarantees the data protection and Detects fraud.
We saw previously on this blog What was NLP as well as its main features. Now let's look at the use cases.
NLP can be used to address a variety of business issues. Here is a non-exhaustive list of areas of application of this technology.
The use of automatic language processing (TAL or NLP in English) during the recruitment phase makes it possible to speed up the analysis of CVs and the search for candidates by identifying the profiles that best match the position to be filled.
First, we identify the relevant keywords after removing the bias and gender present in the job description and we generate a corpus of synonyms.
Then, all candidate CVs are compared to this previously defined reference keyword base in order to identify those that most correspond to the profile sought. This first treatment optimizes the time spent analyzing resumes, a highly time-consuming task for recruiters who receive hundreds or even thousands of resumes for each job offer.
Customer reviews are present everywhere on the internet and in considerable numbers: online sales sites, forums, social networks... which makes their valuation very time-consuming if done manually. NLP makes it possible to analyze all of these comments, to identify the feelings relating to a product or service of a brand and to adapt it to best meet the needs of customers.
The NLP also makes it possible to highlight the themes covered in these opinions. Coupled with the analysis of feelings, this can highlight the strengths and weaknesses of a brand for example (for a restaurant, this could be a positive theme related to staff and hospitality for example). Aqsone has developed a solution to analyze the feelings of reviews for restaurants in Toulouse. This solution allows restaurant owners to be able to improve their service based on customer feedback and to know their strengths.
Automatic language processing also helps identify new audiences who are potentially interested in certain products. Indeed, key information can be found by analyzing textual data that has been extracted from various blogs, websites, or social media posts. This allows brands to effectively expand their communication channels and identify the most suitable sites or social networks to place their ads and reach their customers.
Chatbots, which for the vast majority are based on NLP technologies, can provide fast and effective customer service by answering routine questions and handling simple requests at any time of the day.
Customer satisfaction is all the better, and makes it possible to optimize the size of teams dedicated to customer service by assigning only complex tasks to humans.
The capabilities of these chatbots are evolving enormously. This is evidenced by this video from Google, which presented Google Duplex, a voice chatbot capable of having an advanced conversation with a human:
Although the most popular AI technology in the field of health is computer vision (automatic detection of tumors on medical imaging for example), NLP is no exception. Indeed, thanks to this technology, the large-scale automated targeting of patients with this or that pathology is feasible. For example, by cross-referencing all historical patient medical data such as electronic records, hospital reports and other medical records, researchers at Yale University in the United States retrospectively identified patients with a history of carotid stenosis (Source: “Identification of patients with carotid stenosis using natural language processing”).
In addition, in these times of health crisis due to COVID-19, NLP has been of great importance in identifying how the virus works and developing a treatment. Indeed, scientists have used this technology to study protein sequences and determine the genetic backbone of the virus. This operation could be possible by considering a protein, which is an amino acid sequence, as a language where amino acids are the alphabet (Source: “Natural Language Processing in the fight against COVID-19”).
Safety at work is a key aspect on a production or assembly line. Thus, many companies are launching projects with the aim of using as much data as possible available (HR data, production data, prevention and safety data, location data, etc.) in order to better understand the accidents on a site and identify levers of action that will reduce the risks of accidents as much as possible.
At Aqsone, we have applied NLP to accident reports. This made it possible to highlight the recurring appearance of certain terms related to equipment, tools or environmental contexts (slippery ground for example).
The results of this analysis led to the implementation of new safety actions by the business, which made it possible to positively impact accident trends for our client.
The protection of personal data has become a real challenge in order to be in total compliance with the RGPD (General Data Protection Regulation). The objective is therefore to help data protection officers by creating document analysis tools that can identify the presence of personal data in a very short time and that are compatible with legal requirements. NLP makes it possible to browse a large quantity of files and to highlight any element that may be related to personal data (RIB, medical exams, etc.). Once sensitive documents have been identified, the data protection department can take the necessary actions to ensure their protection. Aqsone developed a solution that makes it possible to identify personal data, which allowed a customer to qualify the nature of the documents in order to protect them in the event of a cyber attack.
Internal fraud costs French businesses 5% of their turnover. There is therefore a real challenge to put in place the necessary actions to fight against it. Aqsone worked for these customers on the detection of expense report fraud. Thanks to NLP it was possible to identify the markers most useful for detecting fraud, the following information was extracted from the tickets: the total amount, the date, the location, the presence or absence of alcohol, and the presence or absence of a supermarket name. These different characteristics were obtained using various NLP techniques.
