Disclosure of Invention
The invention aims to provide a self-learning type law consultation robot to solve the problem that the conventional system for law consultation cannot automatically update the law-related information.
The basic scheme provided by the invention is as follows: a self-learning type law consultation robot comprises an answer bank storage module, a law clause storage module, an answer information generation module and an adjustment module;
the answer bank storage module is used for storing answer information; the legal provision storage module is used for storing the legal opinion book generation basic material;
the answer information generating module is used for searching legal opinions related to the related questions in the legal provision storage module to generate basic materials as answer information when the questions submitted by the consultant do not find the corresponding answer information in the answer library storage module, and then sending the answer information to the adjusting module;
the adjustment module is used for receiving the answer information sent by the answer information generation module, judging whether the answer information is correct answer information of the question, playing the answer information when the judgment result is that the answer information is correct, and adding a screening condition on the basis of the question asked by the consultant and sending the screening condition to the answer information generation module if the judgment result is that the answer information is not correct answer information.
The working principle and the advantages of the invention are as follows: when the consultant carries out legal consultation through the legal consultation robot, if the question of the consultant belongs to the question stored in the existing answer bank storage module, the answer information does not need to be generated by the answer information generation module, if the questions provided by the consultant are already stored in the answer database storage module, then the corresponding legal opinions are searched in the legal provision storage module by the solution information generation module according to the questions provided by the consultant to generate the basic materials as the solution information, and then sending the answer information to an adjusting module to judge whether the answer information is correct or not, storing the answer information into an answer library storage module when the answer information is correct, and adding a screening condition on the basis of the questions asked by the consultant and then sending the answer information to an answer information generating module to search the answer information again if the answer information is wrong.
Compared with the prior art, the scheme realizes the automatic enrichment of the answer information in the answer library storage module through the adjusting module, and before the answer information is stored, the adjusting module can judge whether the answer information is correct or not, so that the wrong answer information is prevented from being stored in the answer library storage module; meanwhile, when the answer information is wrong, the answer information is searched again, so that each question of the consultant can be answered.
Further, the answer base storage module and the law clause storage module are arranged in the consultation robot terminal, the adjusting module is arranged in the adjusting terminal and is in signal connection with the consultation robot terminal, and the adjusting module is used for judging whether answer information is correct or not according to the obtained law professional.
And judging whether the answer information is correct or not by legal professionals, so that the judgment result is more accurate.
Further, an answer base storage module, a legal provision storage module, an answer information generation module and an adjustment module are arranged in the consultation robot terminal, and the adjustment module is used for obtaining a judgment result whether answer information is correct or not by a consultant.
The adjustment module is arranged in the robot terminal, and whether the answer information is correct or not is judged by the consultant, namely whether the answer information is the answer information required by the consultant or not is judged, so that the answer information better meets the requirements of the consultant.
Further, the consultation robot terminal also comprises a correlation information extraction module, and the correlation information extraction module is used for taking the questions submitted by the consultant and the answer information related to the questions submitted as correlation information.
When a consultant consults a question, in order to better understand the consulted question, the relevant information of the consulted question is understood, the relevant information is extracted to be convenient for recommending the relevant information to the consultant,
The consultation robot terminal further comprises a voice acquisition and judgment module and a related problem extraction module, wherein the voice acquisition and judgment module is used for extracting keywords of the consultation problems when the consultant consults the problems, then arranging the extracted keywords in sequence according to extraction time to generate a time axis, and sending the generated time axis to the related information output module; the correlation problem extraction module is used for judging which correlation information is not consulted by the consultant in consultation according to the keywords in the time axis and extracting the correlation information which is not consulted by the consultant.
Through the generation of the time axis, the problem that the associated information output module recommends the consultant to consultant when the associated information is output is avoided.
And the system further comprises an associated information output module, wherein the associated information output module is used for carrying out voice output on the associated information extracted by the associated problem extraction module.
The associated information is output in a voice mode through the associated information output module, and a consultant can know the associated information of the consulted problem conveniently.
Detailed Description
The following is further detailed by the specific embodiments:
examples
As shown in fig. 1 and 2: the utility model provides a self-learning formula law consultation robot, includes adjustment terminal and consultation robot terminal, and consultation robot terminal communicates through wireless communication module and adjustment terminal, and wireless communication module chooses for use the WIFI communication module of current Risym brand. The adjusting terminal can be an existing mobile phone or a computer.
Firstly, the adjustment terminal includes:
the adjusting module is used for judging whether the matching between the question and the legal opinion book in the answering information is correct or not by the staff; after the answer information generation module sends the answer information to the adjustment module, the adjustment module displays the answer information for a worker to check, the worker judges whether the question and the legal comment book in the answer information are correctly matched or not, and then the judgment result is input. And when the judgment result information is input, if the question is matched with the legal opinion book, the input judgment result information is right, and if the question is not matched with the legal opinion book, the input judgment result information is that the worker obtains a keyword related to the legal opinion book generation base material to be searched according to the question. When the staff judges that the matching between the question and the legal opinion book is correct, the judgment result information is input from the adjusting module, if the question and the legal opinion book are matched, the adjusting module stores the answer information corresponding to the judgment result information into the answer library storage module, and meanwhile, the adjusting module sends the answer information to the voice output module. When the staff judges that the matching between the question and the legal opinion book is wrong, the adjusting module sends the judgment result information and the question information in the answer information corresponding to the judgment result information to the answer information generating module.
The consultation robot terminal comprises:
and the legal provision storage module is internally stored with legal opinion book generation basic materials such as legal laws, judicial interpretations, local laws, department regulations and cases of each department and committees and the like which are refined and arranged by professional lawyers. And the answer library storage module is used for storing answer information, and the answer information comprises question questions and legal opinion books corresponding to the question questions.
And the consultation module is used for inputting the voice information of the legal consultation problem by the consultant and then sending the consulted problem to the analysis module.
The analysis module is used for receiving the voice information sent by the consultation module, converting the voice information into text information, matching answer information suitable for the text information in the answer library storage module according to the environment where the text information is suitable, life general knowledge related to the text information, the legal field related to the text information and the like, judging whether the text information corresponds to the answer information according to the matching degree of the question and the text information in the answer information when the answer information is matched, and sending the answer information to the adjustment module and the voice output module when the matching degree of the question and the text information in the answer information is up to 90%.
And the voice output module is used for receiving the answer information sent by the analysis module and the adjustment module, then carrying out voice output on the legal opinions in the answer information, namely, answering the questions proposed by the consultants, and then sending the associated question output request to the associated question extraction module.
And the answer information generating module is used for receiving the text information sent by the analyzing module, then matching the text information with the legal opinion book generation base materials stored in the legal provision storage module, and when the matching degree of the text information and the legal opinion book generation base materials reaches 90%, using the legal opinion book generation base material information as a legal opinion book, using the text information as a question, and then combining the question and the legal opinion book into answer information to be sent to the adjusting module. The answer information generation module is also used for receiving the answer information sent by the adjustment module and judgment result information corresponding to the answer information, matching text information in the answer information and the judgment result information with legal opinion book generation base materials after the answer information generation module receives the answer information and the judgment result information sent by the adjustment module, and when the matching degree of the text information and the legal opinion book generation base materials reaches 90%, using the legal opinion book generation base material information as a legal opinion book, using the text information as a question, and then combining the question and the legal opinion book into the answer information to be sent to the adjustment module.
In specific implementation, the implementation process comprises the following steps:
s1, voice input: a counselor needing to carry out legal consultation inputs voice information of legal problems through a consultation module of the consultation robot terminal, and then the consultation module sends the input voice information to the server.
S2, voice analysis: after the voice analysis module receives the voice information sent by the consultation module, the received voice information is analyzed into text information through a voice analysis technology of the science university news Fei Bingzi company, the text information is matched with question questions stored in the question bank storage module, and when the matching degree of the text information and the question questions is up to 90%, a legal opinion book corresponding to the question questions is sent to the voice output module; and if the matching degree of the text information and the question is lower than 90%, the text information is sent to the answer information generation module.
S3, voice output: and after receiving the answer information sent by the analysis module and the adjustment module, the voice output module in the consultation robot terminal outputs the legal opinions in the answer information in a voice mode, namely, answers the questions proposed by the consultant.
S4, solution information generation: and after receiving the text information sent by the voice analysis module, the answer information generation module matches the text information with the legal opinion generation base material stored in the legal provision storage module, and when the matching degree of the text information and the legal opinion generation base material reaches 90%, the legal opinion generation base material information is used as a legal opinion book, the text information is used as a question, and then the question and the legal opinion book are combined into answer information to be sent to the adjustment module.
S5, judging whether the answer information is correct: after receiving the answer information sent by the answer information generation module, an adjustment module in the adjustment terminal displays the answer information for a worker to check, the worker judges whether the question and the legal comment book in the answer information are correctly matched or not, and then text input of a judgment result is carried out; and when the judgment result information is input, if the question is matched with the legal opinion book, the input judgment result information is right, and if the question is not matched with the legal opinion book, the input judgment result information is that the operator obtains voice information related to the legal opinion book generation base material required to be searched according to the question. When the staff judges that the matching between the question and the legal opinion book is correct, the judgment result information is input from the adjustment module, if the question and the legal opinion book are matched, the adjustment module stores the answer information corresponding to the judgment result information into the answer library storage module, meanwhile, the adjustment module sends the answer information to the voice output module, and when the staff judges that the matching between the question and the legal opinion book is wrong, the adjustment module sends the judgment result information and the question information in the answer information corresponding to the judgment result information to the answer information generation module.
S6, adjustment of answer information: after receiving the answer information sent by the adjusting module and the judgment result information corresponding to the answer information, the answer information generating module matches text information in the answer information and the judgment result information with legal opinion book generation base materials, when the matching degree of the text information and the legal opinion book generation base materials reaches 90%, the legal opinion book generation base material information is used as a legal opinion book, the text information is used as a question, and then the question and the legal opinion book are combined into answer information to be sent to the adjusting module.
Example two
As shown in fig. 3, the difference between the second embodiment and the first embodiment is that the advisory robot in the second embodiment further comprises:
and the associated information storage module is used for storing the answer information and the associated information related to the answer information.
And the intelligent question storage module is used for storing the associated information which is often inquired by the consultant as the associated information in the answer information.
A correlation problem searching module, configured to receive the determination request sent by the correlation problem extracting module, and output a voice "do correlation problem understanding or not after receiving the determination request? The associated question seeking module feeds back the answer information of the consultant to the associated question extracting module when the consultant answers 'needs' through the consulting module.
And the associated information output module is used for receiving the associated information sent by the associated problem extraction module, performing voice playing on the problem questions in the associated information, enabling the consultant to select the problem questions needing to be played with the legal suggestion book, then outputting the problem questions needing to be played with the legal suggestion book in a voice input mode by the consultant, and performing voice playing on the legal suggestion book corresponding to the input problem questions after the consultant inputs the problem questions needing to be played through the voice output module.
And the intelligent voice playing module is used for receiving the associated information sent by the screening module and then automatically playing the associated information.
And the question relevance combination module is used for extracting the answer information from the answer library storage module, then sequentially extracting the key words from the questions of the answer information, matching the key words with the legal opinions in other answer information, combining the two pieces of answer information successfully matched with the key words into relevance information when the key words exist in the legal opinions in other answer information, and then sending the relevance information to the relevance information storage module for storage. For example: the keywords respectively extracted in the different legal opinions now include: the keywords of divorce, injury, traffic accident, property, child and loan are matched when the keywords are matched with the keywords in the legal opinions book of other answer information, the keywords of divorce, property and child are successfully matched, the keywords of traffic accident, injury and loan are also successfully matched, and the answer information of the successfully matched keywords is combined into the associated information.
And the associated problem extraction module is used for receiving the output request sent by the voice output module, extracting associated information related to the problem provided by the consultant from the associated information storage module after receiving the output request, searching the associated information related to the problem provided by the consultant but not consulted according to the sequence of the time axis, and then sending a judgment request for judging whether the associated information is output to the associated problem searching module. And after the associated question extraction module receives the inquirer answer information fed back by the associated question seeking module, the associated question extraction module sends corresponding associated information to the associated information output module.
And the associated problem adjusting module is used for recording and counting the problem topics which need to be played by the legal opinion book and are input by the consultant on the associated information output module, also used for counting the probability that the two problem topics are successively proposed within 20 minutes, then taking the answer information corresponding to the two problem topics, the probability of which is successively proposed within 20 minutes is higher than 80%, as associated information, and storing the associated information into the associated information storage module to cover the original related associated information of the two problem topics. When the probability that two questions are presented in sequence within 20 minutes is higher than 98%, the two questions are stored as associated information in the intelligent question storage module.
And the screening module is used for receiving the time axis sent by the voice acquisition and judgment module, searching the associated information matched with the keyword in the intelligent question storage module according to the keyword closest to the time axis, matching the keyword on the time axis with the answer information in the associated information, corresponding the answer information with the matching rate higher than 90% to the time axis, and sending the associated information which does not correspond to the time axis to the intelligent voice playing module.
And the voice acquisition and judgment module is used for extracting the keywords when the consultant inputs voice through the consultation module, and then arranging the extracted keywords into a time shaft in sequence and sending the time shaft to the screening module. And the voice acquisition and judgment module restarts acquiring the keywords in the input voice after receiving the interruption instruction sent by the time axis updating module, and then rearranges the extracted keywords into the time axis according to the extraction time and sends the time axis to the screening module.
And the time axis updating module is used for extracting keywords from the two adjacent input voices respectively when a consultant performs voice input, judging the relevance between the two keywords after the keywords are extracted, and sending an interruption instruction to the voice acquisition and judgment module when the relevance between the two keywords is lower than 60 percent.
As shown in fig. 4, in the specific implementation, the specific implementation flow is as follows:
s1, voice input: the counselor who needs to make legal counseling inputs the voice information of legal questions through the counseling module of the counseling robot terminal, and then the counseling module sends the input voice information to the server, and then the process goes to steps S2, S7 and S10.
S2, voice analysis: after the voice analysis module receives the voice information sent by the consultation module, the received voice information is analyzed into text information through a voice analysis technology of the science university news Fei Bingzi company, the text information is matched with the question stored in the answer sheet storage module, when the matching degree of the text information and the question reaches 90%, a legal opinion book corresponding to the question is sent to the voice output module, and the step S3 is entered; if the matching degree of the text information and the question is lower than 90%, the text information is sent to the answer information generation module, and then the process goes to step S11.
S3, voice output: after receiving the answer information sent by the analysis module and the adjustment module, the voice output module in the consulting robot terminal outputs the legal opinions in the answer information in a voice manner, namely, answers the questions proposed by the consultant, then sends a related question output request to the related question extraction module, and then the step S4 is carried out.
S4, extracting associated problems: after receiving the output request sent by the voice output module, the associated problem extraction module extracts associated information related to the problem provided by the consultant from the associated information storage module, then the time sequence of the problem provided by the consultant searches for associated information related to the problem provided by the consultant but not consulted in the associated information, and then sends a request for judging whether the associated information is output to the associated problem search module, and the step S5 is entered.
S5, inquiring whether the associated information needs to be: after the associated question seeking module of the consultation robot terminal receives the judgment request sent by the associated question extracting module, the confirmation information of 'whether the associated question needs to be known' is output in a voice mode, when the consultant answers 'need' through the consultation module, the associated question seeking module sends the answer information of the consultant to the associated question extracting module, and then the step S6 is carried out.
S6, outputting the related information: after the associated question extraction module receives the advisor answer information fed back by the associated question seeking module, corresponding associated information is sent to an associated information output module in the advisory robot terminal, after the associated information output module receives the associated information sent by the associated question extraction module, the question in the associated information is played in voice, the advisor selects the question needing to play the legal suggestion book, then the advisor outputs the question needing to play the legal suggestion book in a voice input mode, after the advisor inputs the question needing to play through the voice output module, the legal suggestion book corresponding to the input question is played in voice, and the process enters step S7.
S7, keyword extraction time axis generation: the voice collecting and judging module in the counseling robot terminal extracts the keywords when the counselor inputs the voice through the counseling module, then arranges the extracted keywords in time sequence to a time axis and sends the time axis to the screening module, and the step S8 is entered.
S8, screening associated information: after receiving the time axis sent by the voice acquisition and judgment module, the screening module searches for associated information matched with the keyword in the intelligent question storage module according to the keyword closest to the time axis, then matches the keyword on the time axis with answer information in the associated information, corresponds the answer information with a matching rate higher than 90% to the time axis, sends the associated information which is not corresponding to the time axis to the intelligent voice playing module, and then enters step S9.
S9, intelligent voice playing: the intelligent voice playing module in the consultation robot terminal receives the associated information sent by the screening module, automatically carries out voice playing on the associated information, and then, the step S10 is carried out.
S10, time axis updating: a time axis updating module in the consultation robot terminal extracts keywords from the voice input of the consultant in two adjacent times respectively when the consultant inputs the voice through the consultation module, judges the relevance between the two keywords after the keywords are extracted, and sends an interruption instruction to the voice acquisition judging module when the relevance between the two keywords is lower than 60%; after receiving the interruption instruction sent by the time axis updating module, the voice collection and judgment module restarts collecting the keywords in the input voice, then rearranges the extracted keywords into the time axis according to the extraction time, sends the time axis to the screening module, and then enters step S11.
S11, solution information generation: and after receiving the text information sent by the analysis module, the answer information generation module matches the text information with the legal opinion book generation base material stored in the legal provision storage module, and when the matching degree of the text information and the legal opinion book generation base material reaches 90%, the legal opinion book generation base material information is used as a legal opinion book, the text information is used as a question, the question and the legal opinion book are combined into answer information and sent to the adjustment module, and the steps S12 and S2 are performed.
S12, judging whether the answer information is correct: after receiving the answer information sent by the answer information generation module, an adjustment module in the adjustment terminal displays the answer information for a worker to check, the worker judges whether the question and the legal comment book in the answer information are correctly matched or not, and then text input of a judgment result is carried out; and when the judgment result information is input, if the question is matched with the legal opinion book, the input judgment result information is right, and if the question is not matched with the legal opinion book, the input judgment result information is a keyword which is related to the legal opinion book generation base material required to be searched and obtained by the staff according to the question. When the staff judges that the matching between the question and the legal opinion book is correct, the judgment result information is input from the adjustment module, if the question and the legal opinion book are matched, the adjustment module stores the answer information corresponding to the judgment result information into the answer library storage module, and meanwhile, the adjustment module sends the answer information to the voice output module, and the step S3 is entered. When the worker judges that the matching between the question and the legal comment book is wrong, the adjustment module sends the judgment result information and the question information in the answer information corresponding to the judgment result information to the answer information generation module, and the process goes to step S13.
S13, adjustment of answer information: after receiving the answer information sent by the adjusting module and the judgment result information corresponding to the answer information, the answer information generating module matches the keywords in the answer information and the judgment result information with the legal opinion generating base material, when the matching degree of the keywords and the legal opinion generating base material reaches 90%, the legal opinion generating base material information is used as a legal opinion book, the text information is used as a question, then the question and the legal opinion book are combined into answer information to be sent to the adjusting module, and the step S12 is entered.
EXAMPLE III
The third embodiment is different from the second embodiment in that the adjusting module is located in the consultation robot terminal instead of the adjusting terminal;
the adjustment terminal is used for the consultant to judge whether the answer information is correctly matched with the question object of the consultant; after the answer information generation module sends the answer information to the adjustment module, the adjustment module carries out voice playing on the answer information, and a consultant judges whether the question and the legal comment book in the answer information are correctly matched or not and then inputs a judgment result. When the judgment result information is input, if the question is matched with the legal opinion book, the input judgment result information is 'right', if the question is not matched with the legal opinion book, the input judgment result information is 'wrong', and meanwhile, a consultant speaks a keyword related to the legal opinion book generation base material required to be searched according to the question. When the consultant judges that the question and the legal opinion book are correctly matched, the judgment result information is input from the adjusting module, if the question and the legal opinion book are matched, the adjusting module stores the answer information corresponding to the judgment result information into the answer library storage module, and meanwhile, the adjusting module sends the answer information to the voice output module. When the consultant judges that the question and the legal opinion book are matched incorrectly, the adjusting module sends the judgment result information and the question information in the answer information corresponding to the judgment result information to the answer information generating module.
Example four
The difference between the fourth embodiment and the third embodiment is that in the fourth embodiment, no adjustment terminal is provided, but a consultation question unanswered recording module is arranged in the server, and the consultation question unanswered recording module is used for recording question questions of the unanswered consultants when the answer information generation module does not generate proper answer information, and professional attorneys make corresponding legal notes after collectively processing the questions and store the legal notes in the answer question bank storage module. Therefore, the professional lawyer does not need to answer the legal consultation problem at every moment, only needs to answer at a fixed time every day, and the consultant can know the answer information only by inquiring after the professional lawyer answers the consultation problem, so that the accuracy of the answer information is ensured.
EXAMPLE five
The difference between the fifth embodiment and the fourth embodiment is that the server in the fourth embodiment further includes a non-associated question query module, the non-associated question query module is configured to send answer information that is not associated with the counseling question of the counselor when the counselor starts to counsel the required counseling question (the absence of association means that the question and the answer information provided by the counselor are not associated with each other) to the voice output module for voice output, then the counselor inputs the answer information through the counseling module, and then matching and outputting of the answer information of the counseling question required by the counselor is started. When the answer information is output, the question questions of the answer information are mainly output, and when the time axis is generated, the answer information sent to the voice output module by the non-associated question consultation module and keywords extracted from the response voice information of the consultant are not used as the basis for generating the time axis and updating the time axis.
And the emotion judging module is used for judging the emotion contained in the voice information when the consultant inputs other problems after the response information is input according to the response voice information of the consultant, and then sending the emotion information contained in the voice information to the information authenticity judging module. The reason why the emotion judgment module judges the emotion of the voice information input by the consultant according to the response voice information is that when the consultant inputs the response voice information, the answer information output by the non-associated question inquiry module is not related to the question to be consulted by the consultant, so that the consultant feels puzzled when hearing the question in the answer information, but under normal conditions, the consultant feels puzzled but feels that the consultation of the answer information is necessarily related to the consultation question required by the consultant or has a certain purpose, so that the consultant can input the response voice information more calmly in the puzzled state. When the emotion of voice information input by a consultant in a consultation problem after consultation is judged according to the response voice information, the speed and the volume of the consultant in the response voice information are judged, then the voice information input by the consultant in a consultation process after consultation is compared with the speed and the volume of the response voice information to judge the increase of the speed and the volume, the emotion contained in the voice information input by the consultant in a consultation process is judged according to the increase of the speed and the volume of the voice information input by the consultant in a consultation process of the consultant, and the excitement degree of the consultant is mainly analyzed in an emotion analysis process.
And the information authenticity judging module is used for receiving the emotion information sent by the emotion judging module and judging the authenticity of the content contained in the corresponding voice information according to the emotion information. And when the information authenticity judging module judges the authenticity of the content contained in the voice information, judging the authenticity of the content expressed in the voice information according to the excitement degree of the voice information input by the consultant. Since a person often exaggerates the fact and speaks toward himself/herself when referring to his/her interests or arousing the committee, that is, the content of speaking is more advantageous to himself/herself, if the answer information is matched according to the voice information input by the counselor in the first embodiment, the practicability or fitness of the answer information that is possibly matched is lowered, and therefore, the authenticity is judged in order to match the answer information more appropriately according to the authenticity of the content expressed by the voice information.
When the answer information generation module matches the answer information according to the authenticity of the content expressed by the voice information, according to the reduction of the authenticity of the content expressed by the voice information, the output answer information has more related possibility, namely, the more excited a consultant, the lower the authenticity of the content expressed by the input voice information, the more related possibility in the corresponding output answer information, and the larger the information content in the answer information, so that the consultant can know the answer information which is closest to the expression content of the input voice information and can obtain the answer information under the condition that the expression content of the voice information of the consultant is opposite.
The foregoing is merely an example of the present invention, and common general knowledge in the field of known specific structures and characteristics is not described herein in any greater extent than that known in the art at the filing date or prior to the priority date of the application, so that those skilled in the art can now appreciate that all of the above-described techniques in this field and have the ability to apply routine experimentation before this date can be combined with one or more of the present teachings to complete and implement the present invention, and that certain typical known structures or known methods do not pose any impediments to the implementation of the present invention by those skilled in the art. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several variations and modifications can be made, which should also be considered as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the utility of the patent. The scope of the claims of the present application shall be defined by the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.