Intelligent civil case prediction system and method combining spoken language description and questions answering

Abstract

The invention relates to an intelligent civil case prediction method combining spoken language description and question answering. The method comprises the following steps: S1, receiving a spoken language case description input by a user; S2, determining a consultation intention of the user according to the spoken language case description; S3, detecting whether the feature content is complete ornot according to the consulting intention, if yes, executing the step S4, and if not, prompting the user to supplement the corresponding feature content; and S4, calling the prediction model to outputa corresponding consultation result to the user according to the complete feature content. A pure question and answer mode is converted into a mode of supplementing and combining a small number of questions based on oral description, so that the number of the questions needing to be passively answered by the user is reduced, and the user experience and the completion rate are improved.

Description

technical field [0001] The invention belongs to the technical field of legal services, and in particular relates to an intelligent civil case prediction system and method combining colloquial description and question-and-answer. Background technique [0002] As the country promotes a society ruled by law and citizens pay more and more attention to safeguarding their own rights and interests, the society's demand for legal services is also increasing. At present, there are only public services for online consultation in civil cases in China. Taking professional consultation in the civil field as an example, it includes the following steps, as follows: figure 1 Shown: [0003] 1) The user selects a question type. Here you limit the scope of the consultation by selecting a question type. A typical issue type is a certain claim type under a certain dispute type. [0004] 2) The system pops up a series of questions, which are sorted out by legal business experts, and the answ...

AI Technical Summary

Problems solved by technology

[0009] 2. It does not support colloquial descriptions, that is, natural language input. User input is entirely based on single-choice or multiple-choice question-and-answer forms. The system can only passively collect answers corresponding to pre-prepared questions. However, due to the wide range of legal issues , The personalized reason of the user's question, even after the user answers a series of questions, the question that the user needs to consult most or the key concern point of the user may still not be collected

[0010] 3. The generation of consulting results can only rely on manual sorting, and cannot rely on massive data and learning capabilities based on machine learning and deep learning

[0011] The generation of consulting reports is entirely based on the rules sorted out by humans, which requires a lot of human work by legal professionals; consulting reports can be provided, and the powerful learning capabilities of machines are not used, so intelligence capabilities are not reflected

[0012] 4. Need to ask users a lot of questions, resulting in a very low proportion of users completing the entire consultation process

Questions cannot be dynamically displayed based on the user's choice, the most relevant questions to the user's case, each user who chooses the same question type faces the same question

[0013] Although the above-mentioned online public consultation services have the advantages of convenience and low price, they are far inferior to those of real lawyers due to the aforementioned reasons. However, the number of real lawyers is limited and the consultation fees are high, so that ordinary users still cannot obtain targeted and cost-effective consultation services. Inexpensive Consulting Services

Images