CN112233787A - Animal disease diagnosis system based on chat robot - Google Patents
Animal disease diagnosis system based on chat robot Download PDFInfo
- Publication number
- CN112233787A CN112233787A CN202010980360.8A CN202010980360A CN112233787A CN 112233787 A CN112233787 A CN 112233787A CN 202010980360 A CN202010980360 A CN 202010980360A CN 112233787 A CN112233787 A CN 112233787A
- Authority
- CN
- China
- Prior art keywords
- disease
- module
- diagnosis
- symptom
- intention
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 97
- 208000031295 Animal disease Diseases 0.000 title claims abstract description 17
- 201000010099 disease Diseases 0.000 claims abstract description 123
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 123
- 208000024891 symptom Diseases 0.000 claims abstract description 95
- 230000003993 interaction Effects 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 abstract description 6
- 241001465754 Metazoa Species 0.000 description 14
- 206010012735 Diarrhoea Diseases 0.000 description 9
- 238000012545 processing Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 4
- 244000144972 livestock Species 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000009395 breeding Methods 0.000 description 2
- 230000001488 breeding effect Effects 0.000 description 2
- 230000035622 drinking Effects 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000037406 food intake Effects 0.000 description 2
- 201000001320 Atherosclerosis Diseases 0.000 description 1
- 206010004016 Bacterial diarrhoea Diseases 0.000 description 1
- 206010010774 Constipation Diseases 0.000 description 1
- 206010028735 Nasal congestion Diseases 0.000 description 1
- 206010060860 Neurological symptom Diseases 0.000 description 1
- 206010039101 Rhinorrhoea Diseases 0.000 description 1
- 206010051511 Viral diarrhoea Diseases 0.000 description 1
- 238000009360 aquaculture Methods 0.000 description 1
- 244000144974 aquaculture Species 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000009313 farming Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 208000010753 nasal discharge Diseases 0.000 description 1
- 238000004171 remote diagnosis Methods 0.000 description 1
- 238000009317 small scale farming Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The animal disease diagnosis system based on the chat robot comprises an intention acquisition module, a judgment module and a judgment module, wherein the intention acquisition module is used for acquiring the semantic intention of a farmer to judge whether the semantic intention is a diagnosis class; the symptom parameter acquisition module is used for analyzing and calculating the acquired intention to obtain a fact symptom parameter; a diagnostic module for determining a disease or disease type based on the factual symptom parameters. The intention acquisition module continuously acquires semantic intentions through the communication content of the farmer and the robot until the semantic intentions are determined as diagnosis types; the symptom parameter acquisition module analyzes and calculates the semantic intention and obtains symptom parameters through continuous question-answer interaction between the robot and farmers; finally, the obtained symptom parameters are judged according to multiple veterinary logics, the types of diseases are diagnosed step by step, descriptions of the symptoms of the diseases are obtained through the conversation between the raisers and the robots, the types of the diseases or the diseases are judged on line, the communication efficiency is improved, and the problem of low diagnosis efficiency of the answer form of the questionnaire survey is solved.
Description
Technical Field
The embodiment of the invention relates to the technical field of disease diagnosis of cultured livestock animals, in particular to an animal disease diagnosis system based on a chat robot.
Background
In small-scale farming or domestic farming, various problems, such as medical visits, are encountered. They are not much like large-scale farms having their own veterinarians, either by experience or seeking foreign aids, and most often, the veterinarians call, send messages or communicate with video to obtain help, or the veterinarians go to the field for service, while Chinese veterinarians are really short of supply and short of demand and are difficult to immediately arrive at the field. Therefore, software solutions are also currently emerging in the field of veterinary diagnostics, most commonly with tens of choice questions in the form of expert online diagnosis, and questionnaires to arrive at a result.
Problems and drawbacks with the prior art described above:
1) the farmer is not accurate enough to transmit the symptom information of the veterinarian, the judgment of the veterinarian is influenced, and the problem of the mobile phone pixel can be solved, for example, the photographed result is not completely consistent with the result actually seen by the veterinarian on the spot, and the judgment of the veterinarian is influenced. The disease diagnosis method can also be a problem that the specialty of farmers is not enough, the oral description symptoms are not clear, such as 'my piglets are thin and yellow liquid', the implicit meaning of 'piglet faint yellow water sample diarrhea', 'piglet gray white atherosclerosis diarrhea' and the like, the veterinarian at the telephone has great uncertainty because the symptoms correspond to different suspected diseases, and the descriptions of the farmers are yellow, yellow white or even yellow green, and the water sample or semi-water sample, which are all subjective.
2) The veterinarian does not reply in time, delays the time for primarily taking measures, and causes the loss of the farm, because the part communicating with the farmer is 'people' no matter sending information, making a call or remotely diagnosing by software, the condition of replying in time is inevitable.
3) Several dozens of questions are fixed each time the selected questions in the form of questionnaires are used, answers are obtained through an elimination method after answering, the questions cannot be flexibly adjusted according to cases, accuracy is greatly limited, and the experience process is boring.
Disclosure of Invention
Based on various problems encountered by farmers in the breeding process, for example, the veterinarians in China are difficult to immediately go to the site for first aid due to insufficient supply and demand, the veterinarians cannot accurately describe disease symptoms to influence the judgment of the veterinarians even if the veterinarians are found by calling or sending information, videos, remote diagnosis and the like, meanwhile, the condition that the veterinarians do not reply timely causes the loss of the breeding plants, the self-service diagnosis in the form of questionnaire survey is carried out, the questions are too many and are fixed questions, and the diagnosis result obtained by the elimination method is low in accuracy and tedious. Therefore, the embodiment of the invention provides an animal disease diagnosis system based on a chat robot, farmers speak own problems with the chat robot just like a veterinarian in chatting, the robot navigates to a specified scene through analyzing intentions and entities to interact with the farmers, finally preliminarily diagnoses the direction of the disease, gives treatment scheme suggestions and prevention suggestions, and if the farmers need deeper guidance after interacting with the robot, the online veterinarian can be directly contacted, so that the service mode of the robot and an artificial veterinarian well adapts to the demands of the farmers and supplements the defects of the prior art, and the specific technical scheme of the system is as follows:
the animal disease diagnosis system based on the chat robot provided by the embodiment of the invention comprises:
the intention acquisition module is used for acquiring semantic intentions contained in information sent by farmers, acquiring preset feedback questions corresponding to the semantic intentions to the farmers, and repeating the intention acquisition and question feedback steps until the feedback questions are judged to be diseases;
the symptom parameter acquisition module is used for analyzing and calculating the acquired intention and acquiring various types of factual symptom parameters required by disease diagnosis through the continuous question-answer interaction of the robot and the farmer;
a diagnostic module for making multiple veterinary logical judgments based on said factual symptom parameters to determine the disease or type of disease.
Further, the method also comprises the following steps:
a knowledge acquisition module for acquiring knowledge relating to the disease or disease type based on the determined disease or disease type;
and the calling and displaying module is used for calling and displaying the knowledge related to the diseases or the disease types from the database when receiving an instruction that the diseases or the disease types and the knowledge related to the diseases or the disease types need to be learned.
Further, the intention acquisition module includes:
the character information acquisition module is used for acquiring voice information sent by the farmers and converting the voice information into character information; the information sent by the farmers comprises voice information and picture information; the feedback question is in a voice form or a picture form;
the character comparison module is used for comparing the character information with pre-stored disease diagnosis character information, and if the character information is in the pre-stored disease diagnosis character information, judging that the character information is diagnosis character information;
and the judging module is used for acquiring intention information contained in the character information to obtain the semantic intention when the character information is judged to be the diagnosis character information.
Further, the diagnosis confirming module comprises:
the symptom parameter comparison module is used for comparing the acquired factual symptom parameters with preset symptom parameters preset in a database one by one;
the similarity judging module is used for judging the similarity between the fact symptom parameter and a preset symptom parameter when the acquired fact symptom parameter appears in the preset symptom parameter preset in the database of a certain disease;
and the disease diagnosis module is used for diagnosing the disease corresponding to the fact symptom parameter as a diagnosed disease if the similarity reaches a preset similarity threshold value.
Further, the intention acquisition module further comprises a training module for training the text information when the text comparison module compares the text information with the pre-stored disease diagnosis text information and the text information is not in the pre-stored disease diagnosis text information.
Furthermore, the system also comprises an online diagnosis and treatment module which is used for online video conversation and video diagnosis and treatment between farmers and veterinarians.
The system further comprises an offline video processing module, wherein the offline video processing module is used for processing the video information or the picture information uploaded by the farmers, and classifying and identifying the symptom parameters after the symptom parameters are obtained.
Further, the system comprises a man-machine interaction module, wherein the man-machine interaction module is used for returning options for the farmers to select when the robot obtains a plurality of symptom parameters according to the semantic intentions of the farmers.
Further, the system also comprises an intention hit rate checking module which is used for checking the probability that the robot judges the correct diagnosis according to the symptom parameters.
Furthermore, the system also comprises a language mode conversion module which is used for converting the language mode adopted by the dialog between the farmer and the robot.
The animal disease diagnosis system based on the chat robot comprises an intention acquisition module, a diagnosis module and a diagnosis module, wherein the intention acquisition module is used for continuously acquiring semantic intentions of farmers and the robot when the farmers and the robot chat in voice until the animals are judged to be diseases; the symptom parameter acquisition module is used for analyzing and calculating the acquired intention and acquiring various types of symptom parameters required by disease diagnosis through the continuous question-answer interaction of the robot and the farmer; a diagnostic module for making multiple veterinary logical judgments based on the symptom parameters to determine a disease or disease type. The intention acquisition module acquires semantic intentions contained in voice chat information adopted by the farmer and the robot; the symptom parameter acquisition module analyzes and calculates the semantic intention, and obtains symptom parameters through continuous question and answer interaction between the robot and farmers; finally, the obtained symptom parameters are judged according to multiple veterinary logics, diseases or disease types are diagnosed step by step, descriptions of the diseased symptoms are obtained through the conversation between the raisers and the robots, the disease types are judged on line, the communication efficiency is improved, and the problem of low diagnosis efficiency of the answer forms of questionnaire surveys is solved.
Furthermore, the system also comprises an offline video processing module which is used for processing the video information or the picture information uploaded by the farmers, and classifying and identifying the symptom parameters after the symptom parameters are obtained. The system can intelligently calculate the direction of suspected diseases in real time, and first aid measures can be taken. The method can effectively reduce the economic loss brought to the farmers due to untimely diagnosis caused by waiting for veterinarians.
Further, when the system cannot match a disease, or a farmer wants to obtain more detailed help, the system can directly communicate with an online veterinarian in the same software to obtain an artificial answer. Through diagnosing the module on line, be convenient for raiser and animal doctor carry out online video dialogue and video and diagnose, let the animal doctor need not go the scene, just can directly see the animal state that raiser bred, obtain the symptom parameter of sickening directly perceivedly, the animal doctor of being convenient for can more accurate swift diagnosis disease type, raiser also can treat the animal of breed as early as possible, has improved disease diagnosis efficiency, has also improved the managerial efficiency of plant.
Furthermore, the system also comprises a language mode conversion module which is used for converting the language mode adopted by the dialog between the farmer and the robot. The farmers can select Chinese and English modes, thus invisibly expanding the user population. Namely: foreign farmers can also obtain the help of animal disease diagnosis through chatting with the robot.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
The structures, ratios, sizes, and the like shown in the present specification are only used for matching with the contents disclosed in the specification, so that those skilled in the art can understand and read the present invention, and do not limit the conditions for implementing the present invention, so that the present invention has no technical significance, and any structural modifications, changes in the ratio relationship, or adjustments of the sizes, without affecting the functions and purposes of the present invention, should still fall within the scope of the present invention.
Fig. 1 is a preferred schematic block diagram of a chat robot-based animal disease diagnosis system according to an embodiment of the present invention;
fig. 2 is a schematic block diagram of an operation flow of a chat robot-based animal disease diagnosis system according to an embodiment of the present invention.
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a preferred schematic block diagram of a chat robot-based animal disease diagnosis system provided by an embodiment of the present invention includes an intention acquisition module, a symptom parameter acquisition module, and a diagnosis confirmation module. The intention acquisition module is used for acquiring semantic intentions contained in information sent by the farmer, acquiring preset feedback questions corresponding to the semantic intentions to the farmer, and repeating the intention acquisition and question feedback steps until the farmer is judged to be of a diagnosis type; the symptom parameter acquisition module is used for analyzing and calculating the acquired intention and obtaining symptom parameters of various types of factual symptom parameters required by disease diagnosis through the continuous question-answer interaction of the robot and the farmer; and the diagnosis confirming module is used for carrying out multiple veterinary logic judgments according to the factual symptom parameters and confirming the disease or the disease type.
The semantic meaning refers to the text information of the contents that the farmer wants to consult in the collected voice information, the factual symptom parameter refers to the symptom related to the disease for diagnosing the disease, and the symptom is the fact that the current fact occurs on the animal body to be diagnosed; often a disease comprises a plurality of symptoms, for example a cold disease comprises symptoms of nasal discharge, tears, nasal congestion, etc.
The intention acquisition module includes: the character information acquisition module is used for acquiring information sent by the farmers and converting the information into character information; the information sent by the farmers comprises voice information and picture information; the feedback question is in a voice form or a picture form; the character comparison module is used for comparing the character information with pre-stored disease diagnosis character information, and if the character information is in the pre-stored disease diagnosis character information, judging that the character information is diagnosis character information; and the judging module is used for acquiring intention information contained in the character information to obtain the semantic intention when the character information is judged to be the diagnosis character information.
The diagnosis confirming module comprises: the symptom parameter comparison module is used for comparing the acquired factual symptom parameters with preset symptom parameters preset in a database one by one; the similarity judging module is used for judging the similarity between the fact symptom parameter and a preset symptom parameter when the acquired fact symptom parameter appears in the preset symptom parameter preset in the database of a certain disease; and the disease diagnosis module is used for diagnosing the disease corresponding to the fact symptom parameter as a diagnosed disease if the similarity reaches a preset similarity threshold value. In other words, when the robot chats with the farmer, the robot can analyze the intention (diagnosis or non-diagnosis) in the skill range, then continuously identify the intention (i.e. symptom type, such as diarrhea) from each sentence by continuously performing question-answer interaction with the user, continuously calculate and narrow the disease range by the veterinary diagnosis logic in the background (e.g. the range is firstly narrowed to the disease with diarrhea as the main symptom, and then narrowed to bacterial diarrhea or viral diarrhea through a series of symptom information), stop asking the question until the probability of a certain disease or diseases reaches 90% (e.g. the probability of yellow and limy piglets reaches 90%), and recommend the disease(s) to the user. Finally, after the user agrees to learn the knowledge of the disease(s), the system retrieves the knowledge related to the suspected disease from the knowledge base and displays the knowledge to the user.
The preset symptom parameters comprise mortality, morbidity, typical symptoms, diarrhea, ingestion, drinking, nervous symptoms and the like. The method comprises the steps of starting from obtaining semantic intention information contained in farmers, making a dialog tree according to the intention information by a system, asking which questions when the intention information appears, judging whether answers corresponding to the questions have branches, calculating whether the answers corresponding to the questions have certain probabilities or not, namely the diseases(s), namely the intention is the intention of diagnosis, continuing to dialog with users according to the dialog tree after the intention of the diagnosis is determined, and meanwhile, further analyzing and judging symptoms of one or more diseases corresponding to the intention so as to determine the diagnosis. From the disease, for each common disease, diagnostic factors such as mortality, morbidity, typical symptoms, diarrhea, ingestion, drinking, neurological symptoms and the like are preset in advance. All the conversations between the robot and the farmer are then in constant computing. Considering that one symptom information may suspect multiple diseases and may not even be diseases, some general questions are asked to narrow the scope first, and then the questions are asked randomly for the diseases, and the probability of several diseases is calculated at the same time.
The livestock animal disease diagnosis system based on the chat robot comprises an intention acquisition module, a diagnosis module and a diagnosis module, wherein the intention acquisition module is used for continuously acquiring semantic intentions of farmers and the robot when the farmers and the robot chat in voice until the livestock animal disease diagnosis system is judged to be a disease type; the symptom parameter acquisition module is used for analyzing and calculating the acquired intention and acquiring various types of symptom parameters required by disease diagnosis through the continuous question-answer interaction of the robot and the farmer; a diagnostic module for making multiple veterinary logical judgments based on the symptom parameters to determine a disease or disease type. The intention acquisition module acquires semantic intentions contained in voice chat information adopted by the farmer and the robot; the symptom parameter acquisition module analyzes and calculates the semantic intention, and obtains symptom parameters through continuous question and answer interaction between the robot and farmers; finally, the obtained symptom parameters are judged according to multiple veterinary logics, diseases or disease types are diagnosed step by step, descriptions of the diseased symptoms are obtained through the conversation between the raisers and the robots, the disease types are judged on line, the communication efficiency is improved, and the problem of low diagnosis efficiency of the answer forms of questionnaire surveys is solved. Because the robot is embodied in the software, no matter where the farmer is, at what time, only the mobile phone software is opened, and only a network exists, the robot can be chatted to obtain basic help in time. The problem of the feedback that exists in the communication of raiser and the animal doctor of long-range diagnosis and treatment form is untimely is solved. The robot interacts with the user by continuously recognizing the intention, so that the accuracy is higher and the efficiency is improved. The question and answer diagnosis method solves the problems that the questions are too many and are fixed questions, no scene exists and the accuracy is low in the question and answer diagnosis mode in the questionnaire mode.
Further, in an optional embodiment of the present invention, the method further comprises a knowledge acquisition module for acquiring knowledge related to the disease type according to the determined disease type; and the calling and displaying module is used for calling and displaying the disease type related knowledge from the database when receiving an instruction that the disease type and the disease type related knowledge need to be learned. The robot is trained by sufficient veterinary knowledge skills, when the robot chats with farmers, the intention (diagnosis or non-diagnosis) in the skill range can be analyzed, then the intention (symptom type) is continuously recognized from each sentence by continuously performing question-answering interaction with the user, the disease range is continuously calculated and narrowed by the background through veterinary diagnosis logic until the probability of a certain disease or a certain disease reaches 90%, the question is stopped, and the disease(s) is recommended to the user. Finally, after the user agrees to learn the knowledge of the disease(s), the system retrieves the knowledge related to the suspected disease from the knowledge base and displays the knowledge to the user.
Furthermore, the intention hit rate is seen in the background, the intention which is not hit (namely the problem that the robot cannot answer the question) is analyzed and trained, and the robot is enabled to have an increasing intelligence quotient. Therefore, in an embodiment of the present invention, the intention acquisition module further includes a training module, configured to train the text information when the text comparison module compares the text information with pre-stored disease diagnosis text information and the text information is not in the pre-stored disease diagnosis text information.
In an optional embodiment of the invention, the system further comprises an online diagnosis and treatment module, which is used for the farmers and the veterinarians to perform online video conversation and video diagnosis and treatment. The farmers communicate with the veterinarians through the telephone. Farmers describe their own questions and veterinarians ask further questions and then give a treatment recommendation. The online veterinarians communicate one-to-one, and there are two ways, one is to communicate through instant messaging tools (such as WeChat), describe their own problems through text messages, pictures, videos, etc., even video calls, and the veterinarians will synthesize the information they obtain to give a treatment suggestion. The other mode is an online veterinary sitting diagnosis mode in the mobile phone APP, the communication mode is almost the same as that of the prior mode, namely some APPs can be charged according to the diagnosis awareness and the diagnosis times of experts, and some APPs are free.
When the system can not match diseases or farmers want to obtain more detailed help, the system can directly communicate with online veterinarians in the same software to obtain manual answers. Through diagnosing the module on line, be convenient for raiser and animal doctor carry out online video dialogue and video and diagnose, let the animal doctor need not go to the scene, just can directly see the animal state that raiser bred, obtain the symptom parameter of sickening directly perceivedly, the animal doctor of being convenient for can more accurate swift diagnosis go out disease or disease type, raiser also can treat the animal of breed as early as possible, has improved disease diagnosis efficiency, has also improved the managerial efficiency of plant.
In an optional embodiment of the present invention, the system further includes an offline video processing module, configured to process video information or picture information uploaded by the farmers, and after obtaining symptom parameters, classify and identify the symptom parameters. The system comprises an offline video processing module and a symptom parameter classifying and identifying module, wherein the offline video processing module is used for processing video information or picture information uploaded by farmers, and classifying and identifying the symptom parameter after the symptom parameter is obtained. The system can intelligently calculate the direction of suspected diseases in real time, and first aid measures can be taken. The method can effectively reduce the economic loss brought to the farmers due to untimely diagnosis caused by waiting for veterinarians.
In an optional embodiment of the invention, the system further comprises a human-computer interaction module, which is used for returning options for the farmer to select when the robot obtains a plurality of symptom parameters according to the semantic intention of the farmer.
In an optional embodiment of the present invention, the system further comprises an intention hit rate checking module, configured to check a probability that the robot determines that the diagnosis is correct according to the symptom parameter.
The system also comprises a language mode conversion module which is used for converting the language mode adopted by the dialog between the farmer and the robot. And the language mode conversion module is used for converting the language mode adopted by the dialog between the farmer and the robot. The farmers can select Chinese and English modes, thus invisibly expanding the user population. Namely: foreign farmers can also obtain the help of animal disease diagnosis through chatting with the robot.
The embodiment of the present application is specifically described below by using an operation example, referring to fig. 2, which is a schematic block diagram of an operation flow of an animal disease diagnosis system based on a chat robot provided by an embodiment of the present invention, and an aquaculture user speaks a problem to the robot by voice: my piglets had diarrhea; the animal disease diagnosis system based on the chat robot obtains semantic intentions of farmers by adopting a technology of converting voice into characters and a technology of context understanding, analyzes and calculates the semantic intentions, analyzes whether the semantic intentions belong to diagnosis or non-diagnosis, and whether the semantic intentions are related or not. If the intention of the diagnosis class is analyzed, narrowing the disease range according to the intention symptom parameters (entities) and returning the problem, and continuously calculating the probability narrowing range, such as: the robot comprises: do you ask how old day the piglets are in the "diarrhea in piglets" scenario? A farmer: 5 days old; the robot comprises: what color is the stool of diarrhea? Please select the closest color in the following picture. Questions were asked, such as: the robot comprises: according to your description, I suspect a yellow scour of piglets. The robot comprises: piglet yellow scour is XXX, and the prevention and treatment method is XXX. Finally, the words are converted into voice information to be output. The method also analyzes the disease judgment probability, stops returning the problem when the probability reaches 90%, returns the diagnosis result at the same time, replies the diagnosis result to the user, provides the knowledge whether the problem wants to know the disease, converts the characters into voice to output if the problem wants to know the related knowledge of the disease, and calls the related knowledge about the disease in the knowledge base. If the judgment result is non-diagnostic, the knowledge point is directly returned, for example, the sow constipation is mainly caused by XX, and the prevention method is XXX.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (10)
1. A chat robot-based animal disease diagnostic system, comprising:
the intention acquisition module is used for acquiring semantic intentions contained in information sent by the farmers, acquiring preset feedback questions corresponding to the semantic intentions to the farmers, and repeating the intention acquisition and question feedback steps until the diagnosis is judged;
the symptom parameter acquisition module is used for analyzing and calculating the acquired intention and acquiring various types of factual symptom parameters required by disease diagnosis through the continuous question-answer interaction of the robot and the farmer;
a diagnostic module for making multiple veterinary logical judgments based on said factual symptom parameters to determine the disease or type of disease.
2. The system of claim 1, further comprising:
a knowledge acquisition module for acquiring knowledge relating to the disease or disease type based on the determined disease or disease type;
and the calling and displaying module is used for calling and displaying the knowledge related to the diseases or the disease types from the database when receiving an instruction that the diseases or the disease types and the knowledge related to the diseases or the disease types need to be learned.
3. The system of claim 1, wherein the intent acquisition module comprises:
the character information acquisition module is used for acquiring information sent by the farmers and converting the information into character information; the information sent by the farmers comprises voice information and picture information; the feedback question is in a voice form or a picture form;
the character comparison module is used for comparing the character information with pre-stored disease diagnosis character information, and if the character information is in the pre-stored disease diagnosis character information, judging that the character information is diagnosis character information;
and the judging module is used for acquiring intention information contained in the character information to obtain the semantic intention when the character information is judged to be the diagnosis character information.
4. The system of claim 1, wherein the diagnostic module comprises:
the symptom parameter comparison module is used for comparing the acquired factual symptom parameters with preset symptom parameters preset in a database one by one;
the similarity judging module is used for judging the similarity between the fact symptom parameter and a preset symptom parameter when the acquired fact symptom parameter appears in the preset symptom parameter preset in the database of a certain disease;
and the disease diagnosis module is used for diagnosing the disease corresponding to the fact symptom parameter as a diagnosed disease if the similarity reaches a preset similarity threshold value.
5. The system of claim 3, wherein the intention acquisition module further comprises a training module for training the text information when the text comparison module is comparing the text information with pre-stored disease diagnosis text information that is not among the pre-stored disease diagnosis text information.
6. The system of claim 1, further comprising an online diagnosis module for online video conversation and video diagnosis between the farmer and the veterinarian.
7. The system of claim 1, further comprising an offline prediction module, configured to process video information or picture information uploaded by farmers, and after obtaining symptom parameters, classify and identify the symptom parameters.
8. The system of claim 1, further comprising a human-computer interaction module for returning options for the farmer to select when the robot obtains a plurality of symptom parameters according to the semantic intent of the farmer.
9. The system of claim 1, further comprising an intention hit rate viewing module for viewing a probability that the robot determines that a diagnosis is correct based on the symptom parameters.
10. The system of claim 1, further comprising a language mode conversion module for converting a language mode used for a conversation between the farmer and the robot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010980360.8A CN112233787A (en) | 2020-09-17 | 2020-09-17 | Animal disease diagnosis system based on chat robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010980360.8A CN112233787A (en) | 2020-09-17 | 2020-09-17 | Animal disease diagnosis system based on chat robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112233787A true CN112233787A (en) | 2021-01-15 |
Family
ID=74107914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010980360.8A Pending CN112233787A (en) | 2020-09-17 | 2020-09-17 | Animal disease diagnosis system based on chat robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112233787A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815479A (en) * | 2017-01-17 | 2017-06-09 | 北京农信互联科技有限公司 | Livestock cultivates remote diagnosis system and method |
| CN109817329A (en) * | 2019-01-21 | 2019-05-28 | 暗物智能科技(广州)有限公司 | A kind of medical treatment interrogation conversational system and the intensified learning method applied to the system |
| US20190311807A1 (en) * | 2018-04-06 | 2019-10-10 | Curai, Inc. | Systems and methods for responding to healthcare inquiries |
| CN110489566A (en) * | 2019-08-22 | 2019-11-22 | 上海软中信息系统咨询有限公司 | A kind of hospital guide's method of intelligence hospital guide's service robot |
| CN110570944A (en) * | 2019-09-09 | 2019-12-13 | 北京挺好农牧科技有限公司 | method, device and system for intelligently diagnosing diseases and storage medium |
-
2020
- 2020-09-17 CN CN202010980360.8A patent/CN112233787A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815479A (en) * | 2017-01-17 | 2017-06-09 | 北京农信互联科技有限公司 | Livestock cultivates remote diagnosis system and method |
| US20190311807A1 (en) * | 2018-04-06 | 2019-10-10 | Curai, Inc. | Systems and methods for responding to healthcare inquiries |
| CN109817329A (en) * | 2019-01-21 | 2019-05-28 | 暗物智能科技(广州)有限公司 | A kind of medical treatment interrogation conversational system and the intensified learning method applied to the system |
| CN110489566A (en) * | 2019-08-22 | 2019-11-22 | 上海软中信息系统咨询有限公司 | A kind of hospital guide's method of intelligence hospital guide's service robot |
| CN110570944A (en) * | 2019-09-09 | 2019-12-13 | 北京挺好农牧科技有限公司 | method, device and system for intelligently diagnosing diseases and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 张丽等: "基于移动平台的猪疾病诊断系统的设计与实现", 《农业网络信息》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109960723B (en) | Interaction system and method for psychological robot | |
| CN109446387A (en) | A kind of Owners Committee's intelligent Answer System based on artificial intelligence | |
| CN111276148A (en) | Return visit method, system and storage medium based on convolutional neural network | |
| CN112053597A (en) | Artificial seat training and checking method and system | |
| Pardon et al. | Accuracy and inter‐rater reliability of lung auscultation by bovine practitioners when compared with ultrasonographic findings | |
| CN107092692A (en) | The update method and intelligent customer service system of knowledge base | |
| CN111048075A (en) | Intelligent customer service system and intelligent customer service robot | |
| CN106815479A (en) | Livestock cultivates remote diagnosis system and method | |
| CN117493511B (en) | Automatic question-answering system and method in live pig field based on large language model | |
| CN207742815U (en) | One kind is interactive to admire class learning machine | |
| CN107562911A (en) | More wheel interaction probabilistic model training methods and auto-answer method | |
| CN111221945B (en) | Method and device for generating standard question based on user question | |
| CN116824626A (en) | Artificial intelligent identification method for abnormal state of animal | |
| CN112233787A (en) | Animal disease diagnosis system based on chat robot | |
| CN113065687B (en) | Aquaculture method and system based on dissolved oxygen prediction | |
| Agricola et al. | Teachers’ diagnosis of students’ research skills during the mentoring of the undergraduate thesis | |
| CN115689000A (en) | Learning situation intelligent prediction method and system based on whole learning behavior flow | |
| Scott et al. | An evidence-based study of the impact of church and community mobilisation in Tanzania | |
| CN115098661A (en) | Method, electronic device and computer storage medium for assisting disease screening | |
| CN117436614A (en) | Comprehensive service platform for pig breeding | |
| CN103647702B (en) | The system and method for Consumer's Experience in a kind of raising information exchange | |
| Masambuka-Kanchewa et al. | Exploring differences in communication behaviors between organic and conventional farmers | |
| TWM615272U (en) | Smart voice customer service system | |
| CN112861663A (en) | Poultry posture monitoring method and system based on semantic segmentation | |
| CN116339219B (en) | Pet intelligent device control method based on animal physiological parameters |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210115 |