阅读说明：本技术 一种基于人工智能的智慧社区知识库体系的快速建立方法 (Rapid establishing method of intelligent community knowledge base system based on artificial intelligence ) 是由 崔俊 赵凯 于 2021-07-20 设计创作，主要内容包括：本发明提出了一种基于人工智能下社区知识库体系的快速建立方法,对收集的聊天信息进行筛选,留存针对民生类问题的有效聊天语句；对筛选好的聊天语句进行中文分词,利用NLP智能文本分类技术对聊天语句进行分类,得到聊天语句的问题标签,并结合语义分析,对陈述语句进行候选答案抽取、关系推演、吻合程度判断、噪声过滤得到答案匹配度,将匹配度最高的陈述句标识为问题标签的最佳答案；对中文分词的实体词条进行频次判断,选取频次达到阈值的实体词条,对比更新本地问题标签库。本发明不仅能够有效针对新兴知识快速自动的完善社区知识库,避免了人工操作的麻烦,保证了知识库的时效性,并且能够自动追踪热点话题,提高了知识库的专业覆盖量。(The invention provides a quick establishing method of a community knowledge base system based on artificial intelligence, which screens collected chatting information and retains effective chatting sentences aiming at the problems of livelihood; performing Chinese word segmentation on the screened chat sentences, classifying the chat sentences by using an NLP intelligent text classification technology to obtain problem labels of the chat sentences, performing candidate answer extraction, relation deduction, coincidence degree judgment and noise filtration on the statement sentences by combining semantic analysis to obtain answer matching degrees, and identifying the statement sentence with the highest matching degree as the best answer of the problem labels; and performing frequency judgment on the entity entries of the Chinese word segmentation, selecting the entity entries of which the frequency reaches a threshold value, and comparing and updating the local problem label library. The invention not only can effectively and automatically perfect the community knowledge base aiming at emerging knowledge, avoids the trouble of manual operation, ensures the timeliness of the knowledge base, but also can automatically track hot topics and improve the professional coverage of the knowledge base.)

1. A quick establishing method of a community knowledge base system based on artificial intelligence is characterized by comprising the following steps:

step one, establishing a WeChat group by taking a community as a unit;

secondly, implanting group robots to automatically collect chat information by taking streets as units based on the established WeChat groups;

thirdly, screening the collected chatting information and reserving effective chatting sentences aiming at the civil problems;

fourthly, performing Chinese word segmentation on the screened chat sentences, classifying the chat sentences by using an NLP intelligent text classification technology to obtain problem labels of the chat sentences, performing candidate answer extraction, relation deduction, coincidence degree judgment and noise filtration on the statement sentences by combining semantic analysis to obtain answer matching degree, and marking the statement sentence with the highest matching degree as the best answer of the problem labels;

and fifthly, judging the frequency of the entity entries of the Chinese word segmentation, selecting the entity entries of which the frequency reaches a threshold value, and comparing and updating the local problem label library.

2. The method for rapidly establishing a community knowledge base system based on artificial intelligence according to claim 1, wherein in the third step, the collected chat information is screened, and effective chat sentences aiming at the problems of the livelihood type are retained, wherein the effective chat sentences are character information after expressions, voice and video are removed.

3. The method for rapidly establishing a community knowledge base system under artificial intelligence according to claim 1, wherein in the fourth step, Chinese word segmentation is performed on the screened chat sentences, the NLP intelligent text classification technology is used for classifying the civil problems to obtain the problem labels of the chat sentences, the semantic analysis is combined to perform candidate answer extraction, relationship deduction, coincidence degree judgment and noise filtering on the statement sentences to obtain answer matching degrees, and the statement sentence with the highest matching degree is identified as the best answer of the problem label, and the specific method comprises the following steps:

step 4-1, preliminary classification, roughly classifying the data after preliminary screening, using question labels to search out related chat contents in batch according to the classification defined in advance, and storing the question labels in a question-answer data table of a knowledge base in a question-answer mode;

step 4-2, combining semantic and intention analysis technology, aiming at the statement with the question label, obtaining the answer matching degree of the statement through the steps of candidate answer extraction, relation deduction, coincidence degree judgment and noise filtration, and identifying the statement sentence with the highest matching degree as the best answer of the question label;

and 4-3, circulating the step 4-2, and processing all statement sentences under the timing task to obtain an accurate question-answer knowledge base.

4. A rapid establishment system based on a community knowledge base system under artificial intelligence, which is characterized in that the rapid establishment based on the community knowledge base system under artificial intelligence is carried out based on the method of any one of claims 1 to 3.

5. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 3 when executing the computer program, and performs fast establishment of a community knowledge base architecture based on artificial intelligence.

6. A computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method of any one of claims 1-3 for rapid establishment of a community knowledge base architecture based on artificial intelligence.

Technical Field

The invention relates to the field of computer application, in particular to a quick establishment method of a community knowledge base system based on artificial intelligence.

Background

Natural language is used to describe various events in human life, an action or a historical event, and also includes events, places, people, states generated by the events and the connection between the events. With the rise of the internet era, people increasingly rely on social software such as QQ and WeChat to communicate and exchange to obtain information, and the information often presents the characteristics of mass, dramatic increase, redundancy and the like. In order to monitor and use effective information more quickly and effectively, and to solve the problem that efficiency cannot be solved obviously through artificial collection and analysis, it is very important that a computer application can automatically analyze text messages, which is related to the application capability of gradually-rising artificial intelligent conversations in the community management field.

In community management, the knowledge base in the community professional field is combined with an artificial intelligence dialogue system, and compared with other traditional dialogue systems for corpus retrieval, the system has the recognition capability of private knowledge such as community civilians and the like, can understand the words of common people, and enables the common people to feel that the common people are chatting with a professional community network member. However, the traditional knowledge base pursues more domain coverage, the mining of the knowledge in the professional field is insufficient, the reply content in a certain industry is often not accurate enough, the knowledge is relatively old, and the updating frequency is far from reaching the standard.

Disclosure of Invention

The invention aims to provide a quick establishing method of a community knowledge base system based on artificial intelligence.

The technical solution for realizing the purpose of the invention is as follows: a quick establishment method of a community knowledge base system based on artificial intelligence comprises the following steps:

step one, establishing a WeChat group by taking a community as a unit;

secondly, implanting group robots to automatically collect chat information by taking streets as units based on the established WeChat groups;

thirdly, screening the collected chatting information and reserving effective chatting sentences aiming at the civil problems;

fourthly, performing Chinese word segmentation on the screened chat sentences, classifying the chat sentences by using an NLP intelligent text classification technology to obtain problem labels of the chat sentences, performing candidate answer extraction, relation deduction, coincidence degree judgment and noise filtration on the statement sentences by combining semantic analysis to obtain answer matching degree, and marking the statement sentence with the highest matching degree as the best answer of the problem labels;

and fifthly, judging the frequency of the entity entries of the Chinese word segmentation, selecting the entity entries of which the frequency reaches a threshold value, and comparing and updating the local problem label library.

And further, screening the collected chatting information, and reserving effective chatting sentences aiming at the problems of the livelihood, wherein the effective chatting sentences are character information after expressions, voice and video are removed.

Further, the fourth step is to perform Chinese word segmentation on the screened chat sentences, classify the civil problems by using an NLP intelligent text classification technology to obtain problem labels of the chat sentences, perform candidate answer extraction, relationship deduction, coincidence degree judgment and noise filtration on the statement sentences by combining semantic analysis to obtain answer matching degrees, and mark the statement sentence with the highest matching degree as the best answer of the problem labels, wherein the specific method comprises the following steps:

step 4-1, preliminary classification, roughly classifying the data after preliminary screening, using question labels to search out related chat contents in batch according to the classification defined in advance, and storing the question labels in a question-answer data table of a knowledge base in a question-answer mode;

step 4-2, combining semantic and intention analysis technology, aiming at the statement with the question label, obtaining the answer matching degree of the statement through the steps of candidate answer extraction, relation deduction, coincidence degree judgment and noise filtration, and identifying the statement sentence with the highest matching degree as the best answer of the question label;

and 4-3, circulating the step 4-2, and processing all statement sentences under the timing task to obtain an accurate question-answer knowledge base.

A quick establishment system of a community knowledge base system based on artificial intelligence is based on any one of the methods and is used for quickly establishing the community knowledge base system based on artificial intelligence.

A computer device comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes any method when executing the computer program, and the quick establishment of a community knowledge base system based on artificial intelligence is carried out.

A computer-readable storage medium having stored thereon a computer program that, when executed by a processor, implements any of the methods described herein for rapid establishment of a community knowledge base hierarchy based on artificial intelligence.

Compared with the prior art, the invention has the following remarkable advantages: (1) can effectively and quickly collect various civil problems brought forward by residents. (2) The community knowledge base can be effectively improved rapidly and automatically aiming at emerging knowledge, the trouble of manual operation is avoided, and the timeliness of the knowledge base is guaranteed. (3) And hot topics are automatically tracked, and the professional coverage of the knowledge base is improved.

Drawings

FIG. 1 is a flow chart of the method for rapidly establishing the community knowledge base system based on artificial intelligence.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

As shown in fig. 1, a method for quickly establishing a community knowledge base system based on artificial intelligence includes the following steps:

step 1, data acquisition

The WeChat group is established by taking a community as a unit, the WeChat can effectively and quickly reflect the attention points of common people at present, and the attention topics of the common people can be automatically and quickly collected by relying on the powerful functions of the WeChat group robot, and the specific process is as follows:

step 1-1, community building, wherein community network operators build communities according to communities in the jurisdiction range of the community network operators, and the community names are several groups according to a certain rule such as the community names, so that residents can conveniently and quickly add WeChat communities;

and step 1-2, enabling residents to enter a group, and guiding the residents to enter the micro-trust group by each resident committee organization after the micro-trust group is established.

Step 2, data extraction

Based on the first step of embedding the WeChat cluster into the swarm robot, the WeChat cluster can be served for people on line for 7 x 24 hours all day without melting, and is a basic stone for data analysis statistics, and the specific process is as follows:

and implanting a WeChat robot into the established WeChat groups by taking the streets as units, and adding the WeChat robot into each WeChat group to establish the contact between the application and the residents after the WeChat groups of the streets are established.

Step 3, data screening

After the conversation of the residents is collected, screening is carried out on the relevant problems of the residents, and the specific process is as follows:

and storing all the collected text (non-emoticons, voice, video and the like) chatting data into a chatting record library of each community according to the screening rule.

Step 4, data classification

Carrying out topic classification on the effective corpus in the last step by using the existing intelligent word segmentation technology, and identifying the answer matching degree of the statement sentence by combining semantic analysis, wherein the specific process is as follows:

step 4-1, preliminary classification, roughly classifying the data after preliminary screening, using question labels to search out related chat contents in batch according to the classification defined in advance, and storing the question identification labels in a question-answer data table of a knowledge base in a question-answer mode;

and 4-2, combining the existing semantic and intention analysis technology, aiming at the sentences with the problem labels, obtaining the answer matching degree of the statement sentences through the steps of candidate answer extraction, relation deduction, coincidence degree judgment and noise filtration, and identifying the statement sentences with the highest matching degree as the best answers of the problems.

Step 5, perfecting the knowledge base

Setting a timing task, circulating the answer matching operation in the step 4, and continuously optimizing the answers of all the civil problems to improve the knowledge base, wherein the specific process is as follows:

step 5-1, establishing a timing task and selecting a statement of a problem label;

step 5-2, screening statement sentences;

step 5-3, performing semantic and intention analysis on the statement sentence, and inquiring the matching degree of the answer to the question;

step 5-4, sorting according to the matching degree of the answers to obtain the best answer of the question;

and 5-5, processing label updating, selecting entity entries with higher frequency (reaching a threshold value) according to intelligent word segmentation and frequency judgment, and comparing and updating the local problem label library.

The invention also provides a quick establishment system of the community knowledge base system based on artificial intelligence, and the quick establishment of the community knowledge base system based on artificial intelligence is carried out based on any one of the methods.

A computer device comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes any method when executing the computer program, and the quick establishment of a community knowledge base system based on artificial intelligence is carried out.

A computer-readable storage medium having stored thereon a computer program that, when executed by a processor, implements any of the methods described herein for rapid establishment of a community knowledge base hierarchy based on artificial intelligence.

Examples

To verify the validity of the inventive scheme, the following simulation experiment was performed.

A quick establishing method of a community knowledge base system based on artificial intelligence comprises the following steps:

establishing a WeChat group by taking communities as units, averagely establishing 10 groups for each community, and taking a community gridder or a social worker as a group owner;

secondly, implanting swarm robots into the established WeChat swarm, pulling the swarm robots into the swarm by the swarm owner, and starting a swarm chat collection function;

thirdly, screening the collected chatting information aiming at the civil problems, and reserving effective chatting sentences;

fourthly, performing Chinese word segmentation on the screened chat sentences, and classifying the chat sentences by using the existing NLP intelligent text classification technology to obtain problem labels of the chat sentences;

fifthly, analyzing the semanteme and intention of the screened chat sentences, when the attributes of the chat sentences are statement sentences, obtaining answer matching degree of the statement sentences through the steps of candidate answer extraction, relation deduction, coincidence degree judgment and noise filtration, and identifying the statement sentences with the highest matching degree as the best answers of the question labels;

sixthly, a system background creates a timing task, and the answer matching operation in the fifth step is repeated, so that the knowledge base can be continuously optimized and perfected;

and seventhly, selecting entity entries with high frequency (reaching a threshold value) according to Chinese word segmentation and frequency judgment, and comparing and updating the local problem label library. For example, "a case is an asymptomatic confirmed diagnosis case in a certain cell, and a specific hospital is treated? The system obtains entity entries such as 'cell', 'no symptom', 'case', 'fixed point hospital' and the like by using the existing artificial intelligence word segmentation technology, records the occurrence frequency of the entity entries, and if the occurrence frequency is higher than a set threshold value, the system compares the local problem label library and stores new entity entries into the local problem label library.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.