1. An IPTV terminal health consultation method based on intelligent interaction is characterized by comprising the following steps:

positioning a health consultation category field consulted by the user;

acquiring health index information corresponding to the user according to the health consultation category domain;

and generating a customized health consultation result according to the health index information, and feeding the customized health consultation result back to the user through the IPTV.

2. The method of claim 1, further comprising: and after the customized health consultation result is generated, recommending a health problem solution for the user based on the health knowledge map.

3. The method of claim 1, wherein the obtaining of the health index information corresponding to the user according to the health consultation category domain comprises:

calling an inquiry statement normal form based on a multi-round conversation model corresponding to the health consultation category domain;

replacing key query information of the query sentence normal form with user expression, and performing multiple rounds of voice interaction based on the user expression;

and acquiring user input information based on the multiple rounds of voice interaction, and performing variable assignment on the user input information to generate health index information.

4. The method of claim 3, further comprising: determining health index information through interaction of an IPTV, specifically comprising:

the IPTV displays the query sentence normal form and is attached with a corresponding reply option, and a user replies through human-computer interaction so as to determine the health index information;

the man-machine interaction mode comprises physical key interaction, voice interaction or touch interaction.

5. The method of claim 3, wherein the obtaining of the health index information corresponding to the user according to the health consultation category domain further comprises:

generating health index information to be detected based on the health consultation category domain;

and detecting the user by using a health detection device based on the health index information to be detected, and perfecting the health index information to be detected.

6. The method of claim 1, wherein the generating customized health consultation results according to the health index information and feeding back the customized health consultation results to the user through an IPTV comprises:

performing inference decision calculation on the health index information based on the inference decision strategy model;

generating a customized health consultation result by using a format document generation tool based on the result of the inference decision calculation;

feeding back the customized health consultation result to the user through the IPTV;

the form of the feedback to the user through the IPTV is at least one of voice broadcast, animation broadcast and character display.

7. An IPTV terminal health consultation system based on intelligent interaction is characterized by comprising:

the health detection device is used for acquiring body health index information of the user;

the intelligent interaction equipment is used for acquiring a user voice signal, converting the voice signal into text information and performing man-machine interaction with a user;

the cloud server is used for acquiring health index information and generating a customized health consultation result according to the health index information;

the set top box is used for realizing communication between the IPTV and the cloud server as well as between the IPTV and the intelligent interaction equipment;

and the IPTV is used for realizing the broadcasting and/or displaying of the interactive content and the consultation result.

8. The system of claim 7, wherein the cloud server comprises:

the category domain positioning module is used for positioning a health consultation category domain consulted by the user;

the health index acquisition module is used for acquiring health index information corresponding to the user according to the health consultation category domain;

and the result generating module is used for generating a customized health consultation result according to the health index information.

9. The system of claim 8, wherein the health indicator acquisition module comprises:

the query statement calling unit is used for calling a query statement normal form based on the multi-round conversation model corresponding to the health consultation category domain;

the voice interaction unit is used for replacing key inquiry information of the inquiry statement paradigm with user expression and carrying out multi-round voice interaction based on the user expression;

and the health index generation unit is used for acquiring user input information based on the multiple rounds of voice interaction and performing variable assignment on the user input information to generate health index information.

10. The system of claim 8, further comprising:

the IPTV interactive module is used for displaying the query sentence paradigm through IPTV and attaching corresponding reply options, and a user replies through human-computer interaction so as to determine the health index information;

the man-machine interaction mode comprises physical key interaction, voice interaction or touch interaction.

Background

People no longer meet the disease-free state, but pursue higher quality of life, are healthier and longer-lived, and invest more for health than before. Health is closely related to an individual's awareness of health, the surrounding environment, medical care, the individual's biological factors and lifestyle, and self-conducted health care. The life style is controlled by the user, and health care measures are properly taken through adjusting the life style of the user, so that the aim of promoting the health of the user to the maximum extent is fulfilled. However, in combination with the actual situation, modern people face more and more competition and challenges to cope with fast-paced learning, work and life, and people may have aging and pathological changes at any time in physiology and psychology. At present, the incidence rate of chronic diseases is increased year by year, sub-health people are increased day by day, psychological problems are frequent, and the serious threats to human health.

In addition, medical expenses due to health problems are increasing year by year. Health counseling is a mode of health management, which provides counseling services for help seekers to remove health problems. The system and continuous personalized medical care suggestions are provided for the health problems proposed by each social member, so that the health level of people is improved by improving a health maintenance mode, the health risk and the expenditure of medical expenses are effectively reduced, most of the existing health consultation needs a convenient and efficient health consultation mode to meet the requirements of people by requiring consultants to consult with doctors face to face or simply consulting with mobile phones.

Disclosure of Invention

Object of the application

Based on this, in order to save user time, save medical expenses, realize the long-range health consultation under the family environment, the following technical scheme is disclosed in this application.

(II) technical scheme

The application discloses an IPTV terminal health consultation method based on intelligent interaction, which comprises the following steps:

positioning a health consultation category field consulted by the user;

acquiring health index information corresponding to the user according to the health consultation category domain;

and generating a customized health consultation result according to the health index information, and feeding the customized health consultation result back to the user through the IPTV.

In one possible embodiment, the method further comprises: and after the customized health consultation result is generated, recommending a health problem solution for the user based on the health knowledge map.

In one possible embodiment, the locating the health category domain consulted by the user includes:

collecting a user voice signal and converting the voice signal into text information;

obtaining a health consultation intention of the user based on the text information;

locating the health issue category domain based on the health consultation intent.

In a possible implementation manner, the acquiring health index information corresponding to the user according to the health consultation category domain includes:

calling an inquiry statement normal form based on a multi-round conversation model corresponding to the health consultation category domain;

replacing key query information of the query sentence normal form with user expression, and performing multiple rounds of voice interaction based on the user expression;

and acquiring user input information based on the multiple rounds of voice interaction, and performing variable assignment on the user input information to generate health index information.

In one possible embodiment, the method further comprises: determining health condition information through interaction of an IPTV, specifically comprising:

the IPTV displays the query sentence normal form and is attached with a corresponding reply option, and a user replies through human-computer interaction so as to determine the health index information;

the man-machine interaction mode comprises physical key interaction, voice interaction or touch interaction.

In a possible implementation manner, the acquiring health index information corresponding to the user according to the health consultation category domain further includes:

generating health index information to be detected based on the health consultation category domain;

and detecting the user by using a health detection device based on the health index information to be detected, and perfecting the health index information to be detected.

In a possible implementation manner, the generating a customized health consultation result according to the health index information and feeding back the customized health consultation result to the user through an IPTV includes:

performing inference decision calculation on the health index information based on the inference decision strategy model;

generating a customized health consultation result by using a format document generation tool based on the result of the inference decision calculation;

feeding back the customized health consultation result to the user through the IPTV;

the form of the feedback to the user through the IPTV is at least one of voice broadcast, animation broadcast and character display.

As a second aspect of the present application, the present application further discloses an IPTV-end health consultation system based on intelligent interaction, including:

the health detection device is used for acquiring body health index information of the user;

the intelligent interaction equipment is used for acquiring a user voice signal, converting the voice signal into text information and performing man-machine interaction with a user;

the cloud server is used for acquiring health index information and generating a customized health consultation result according to the health index information;

the set top box is used for realizing communication between the IPTV and the cloud server as well as between the IPTV and the intelligent interaction equipment;

and the IPTV is used for realizing the broadcasting and/or displaying of the interactive content and the consultation result.

In one possible embodiment, the cloud server includes:

the category domain positioning module is used for positioning the health category domain consulted by the user;

the health index acquisition module is used for acquiring health index information corresponding to the user according to the health consultation category domain;

and the result generating module is used for generating a customized health consultation result according to the health index information.

In one possible implementation, the health indicator obtaining module includes:

the query statement calling unit is used for calling a query statement normal form based on the multi-round conversation model corresponding to the health consultation category domain;

the voice interaction unit is used for replacing key inquiry information of the inquiry statement paradigm with user expression and carrying out multi-round voice interaction based on the user expression;

and the health index generation unit is used for acquiring user input information based on the multiple rounds of voice interaction and performing variable assignment on the user input information to generate health index information.

In one possible embodiment, the method further comprises:

the IPTV interactive module is used for displaying the query sentence paradigm through IPTV and attaching corresponding reply options, and a user replies through human-computer interaction so as to determine the health index information;

the man-machine interaction mode comprises physical key interaction, voice interaction or touch interaction.

(III) advantageous effects

According to the IPTV terminal health consultation method and system based on intelligent interaction, health consultation is carried out through the cooperation of the health monitoring device, the intelligent interaction equipment, the set top box and the IPTV, user time is saved, medical expenses are saved, and remote health consultation under a home environment is achieved.

Drawings

The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining and illustrating the present application and should not be construed as limiting the scope of the present application.

Fig. 1 is a schematic flow chart of an IPTV-side health consultation method based on intelligent interaction disclosed in the present application.

Fig. 2 is a block diagram of a structure of an IPTV-side health consultation system based on intelligent interaction disclosed in the present application.

Detailed Description

In order to make the implementation objects, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be described in more detail below with reference to the drawings in the embodiments of the present application.

An embodiment of an IPTV-side health consultation method based on intelligent interaction disclosed in the present application is described in detail below with reference to fig. 1. As shown in fig. 1, the method disclosed in this embodiment mainly includes the following steps 100 to 300.

And step 100, positioning a health consultation category domain consulted by the user.

Specifically, first, a classification of the health issue consulted by the user, i.e., the health consultation category field, is obtained, and step 100 includes steps 110 to 130.

Step 110, collecting a user voice signal and converting the voice signal into text information.

Specifically, the user inputs a health problem to be consulted by voice through an intelligent interaction device, the intelligent interaction device comprises a device with voice acquisition and voice recognition functions, the device comprises an intelligent sound box, an intelligent mobile phone and other intelligent electrical appliances, a voice recognition module is arranged in the intelligent interaction device, the voice recognition module converts acquired voice signals into text information, and further the step 110 comprises steps 111 to 113.

And step 111, preprocessing the acquired voice signals.

Specifically, the voice signal acquired by the intelligent interaction device needs to be preprocessed to obtain characteristic parameters, and the characteristic parameters are compared with parameters in a template parameter library to obtain an identification result and obtain text information when a subsequent template is matched conveniently.

And 112, extracting characteristic parameters of the preprocessed voice signals.

Specifically, the characteristic parameters include pitch period, resonance peak value, and the like. The most commonly used comprehensive characteristic parameters are: linear Prediction Cepstral Coefficients (LPCC) and Mel-frequency cepstral coefficients (MFCC). Two kinds of feature parameters are to operate on the speech signal in the cepstrum domain, preferably Mel cepstral coefficients are used as the feature parameters of the speech signal, Mel cepstral coefficients (MFCC) are the most widely used speech feature parameters in speech recognition systems. The method comprises the steps of carrying out pre-emphasis, framing and windowing on an input voice signal, obtaining a frequency spectrum of the signal through fast Fourier transform, enabling the frequency spectrum of the signal to pass through Mel filter banks, outputting logarithmic energy of each filter bank to obtain a logarithmic frequency spectrum, and finally carrying out Discrete Cosine Transform (DCT) on the logarithmic frequency spectrum to obtain a Mel cepstrum coefficient (MFCC) coefficient.

And step 113, acquiring a voice signal recognition result.

Specifically, a pre-trained model is used for speech signal recognition, and the method is preferable. And selecting an HMM model, modeling according to the continuous HMM model, performing model training on the HMM model, performing voice recognition by using the trained HMM model according to the extracted characteristic parameters, and acquiring a recognition result, namely converting the voice signal into text information.

And step 120, obtaining the health consultation intention of the user based on the text information.

Specifically, the health consultation intention of the user is obtained, namely the health consultation purpose of the user is determined, firstly, keywords in the text information are extracted as classification features, and the input information of the user is classified according to the classification features by using an intention recognition model of deep learning to obtain the health consultation intention.

Step 130, positioning the health consultation category domain based on the health consultation intention.

Specifically, the cloud server is provided with a health consultation category domain library. The health consultation domain library is internally provided with different health consultation domains, after the health consultation intention of the user is obtained, the health consultation domains are positioned in the health consultation domain library according to the health consultation intention of the user, and the health consultation domains determine a man-machine conversation mechanism applicable to subsequent multi-round voice interaction, including inquiry sentences, user expressions and the like adopted in man-machine conversation, and also determine health indexes to be detected by the user and the like.

And 200, acquiring health index information corresponding to the user according to the health consultation category domain.

Specifically, according to the determined health consultation category domain, health index information corresponding to the category domain needs to be acquired, so as to generate a corresponding consultation result according to the health index information. Further, step 200 further includes steps 210 to 230.

And step 210, calling a query statement paradigm based on the multi-round conversation model corresponding to the health consultation category domain.

Specifically, the health consultation category domain is disassembled, health characteristic facts in the health consultation category domain are summarized and sorted by capturing key elements of massive examples and expert experience based on machine learning, and a multi-turn dialogue model dialogue library is automatically generated through texts. And calling a corresponding inquiry statement paradigm in a corresponding multi-round dialogue model dialogue library based on the multi-round dialogue model, guiding the user to reply, and perfecting the input health index information so as to output an accurate consultation result.

Step 220, replacing the key query information of the query statement paradigm with a user expression, and performing multiple rounds of voice interaction based on the user expression.

Specifically, part of the query information in the query sentence paradigm called in step 210 is replaced by the user expression to prevent the profession and complexity of the medical wording from causing difficulty for the user to understand, and the user expression can help the user to understand the conversation content to make a more accurate response.

And step 230, acquiring user input information based on the multiple rounds of voice interaction, and performing variable assignment on the user input information to generate health index information.

Specifically, multiple rounds of voice interaction are performed based on the generated multiple rounds of session models, user input information in each round of voice interaction process is collected and assigned to health characteristic variables, and a health characteristic variable set, namely the health index information, is generated.

In at least one embodiment, step 200 further includes step 240, determining health status information through IPTV interaction, which specifically includes:

the IPTV displays the query sentence normal form and is attached with a corresponding reply option, and a user replies through human-computer interaction so as to determine the health index information;

the man-machine interaction mode comprises physical key interaction, voice interaction or touch interaction.

Specifically, when the user of the smart interactive device performs human-computer interaction, the cloud server simultaneously transmits interactive content to the IPTV through the set top box, the IPTV screen may display the query sentence and simultaneously attach a reply option of the query sentence, and the user may directly select the reply option through a physical key, such as a remote controller key, voice interaction, such as direct interaction through a smart speaker, or through touch interaction, such as through the IPTV screen. The multi-round interaction can be independently completed by matching the cloud server with the intelligent voice equipment or the IPTV, and can also be completed by matching the cloud server with the intelligent voice equipment and the IPTV together.

In this embodiment, the cloud server is connected to the set top box and the intelligent interactive device through the lan, the set top box controls the IPTV as a display medium, the IPTV and the intelligent interactive device are also connected through the set top box, the intelligent interactive device realizes interaction with the set top box through the lan or the bluetooth, and the IPTV and the intelligent interactive device cooperate with each other, so that visualization and diversification of intelligent interaction are realized, interaction efficiency is improved, convenience is brought to a user, and user experience is greatly improved.

In at least one embodiment, step 200 further includes steps 250 through 260.

And 250, generating the health index information to be detected based on the health consultation category domain.

Specifically, when the user cannot realize the whole input of the health index only by means of voice input, the real-time health detection is required, the health index information to be detected is generated based on the health consultation category domain, and then the body of the user is detected in real time.

And 260, detecting the user by using a health detection device based on the to-be-detected health index information to perfect the to-be-detected health index information.

Specifically, based on the health index information to be detected, the cloud server reminds the user to connect the health detection device through the intelligent interaction device and/or the IPTV so as to detect the health index, the health detection device can be in direct communication with the cloud server, or the detected health index information of the user is uploaded to the cloud server through human-computer interaction in real time, and preferably, the detected health index comprises body temperature, body fat, blood pressure and the like.

And 300, generating a customized health consultation result according to the health index information, and feeding the customized health consultation result back to the user through the IPTV.

Specifically, after the complete user health index is obtained, the customized health consultation result of the user is generated through inference decision calculation based on the complete health index information, and is fed back to the user through the IPTV, and further, the step 300 includes steps 310 to 330.

And 310, performing inference decision calculation on the health index information based on the inference decision strategy model.

Specifically, after health index information composed of the health characteristic variable set is acquired, inference decision calculation is performed on the health index information by using an inference decision strategy model formed based on expert experience and a large number of cases, and an inference decision calculation result is output.

And 320, generating a customized health consultation result by utilizing a format document generation tool based on the reasoning decision calculation result.

Specifically, a word-format document template is uploaded to the cloud server, and a customized health consultation result with a standard format is automatically generated based on the word-format document template and the inference decision calculation result in step 310.

And step 330, feeding back the customized health consultation result to the user through the IPTV.

Specifically, the cloud server transmits the customized health consultation result to the IPTV through a set top box, and the IPTV feeds back the customized health consultation result to the user through the IPTV.

It should be noted that the form of the feedback to the user through the IPTV is at least one of voice broadcast, animation broadcast, and text display.

Specifically, the IPTV may display the consultation result according to a user requirement, and the display mode includes: speech broadcasting, text display, animation demonstration and the like, and can simultaneously carry out a plurality of demonstration modes, such as: and the voice broadcasting is matched with the text display to feed back the health consultation result.

In the embodiment, multiple display modes of health consultation results are realized through the IPTV, the user experience is improved, and the realization of health consultation in a family environment through the IPTV as a display medium is a brand-new business mode.

In at least one embodiment, step 400 is also included.

And 400, after the customized health consultation result is generated, recommending a health problem solution for the user based on the health knowledge graph.

Specifically, after the health consultation result is obtained, a health problem solution is generated based on the health knowledge map, that is, according to the health consultation result of the user, remote registration and drug recommendation can be performed on the user or a health suggestion can be generated.

In at least one embodiment, after the customized health consultation result is generated, the user still has problems or doubt about the health consultation result, and manual consultation can be performed, namely, real-time online consultation with the cooperative partner and the doctor. Further, the present embodiment is implemented by steps 510 to 520.

Step 510, transmitting the health index information and the health consultation category domain to a health partner, and the health partner screening doctors capable of providing services and feeding back the doctor information on an IPTV.

Specifically, the health index information and the health consultation category domain are transmitted to a health partner, the health partner is a cooperative hospital or other places capable of providing health consultation, doctors in the corresponding domain are screened according to the health consultation category domain, further screening is carried out according to the real-time working state of doctors meeting the requirements, doctors capable of providing health consultation services are screened out, and doctor information is fed back to an IPTV, and the doctor information comprises basic identity information, personal excellence fields, individuals, hospital scores and the like.

In step 520, the user autonomously selects a doctor for consultation through the doctor information displayed by the IPTV.

Specifically, the user can independently select according to doctor information displayed by the IPTV, the system can also randomly match doctors to perform health consultation service, and after a doctor performing the health consultation service is selected, the doctor can be connected with the doctor through the IPTV, and the connection mode can be video call or voice call.

Furthermore, if no matched doctor exists at present, namely all doctors meeting the requirements in the field are in busy states, the appointment service can be performed, the doctor and the user are coordinated to perform the appointment health consultation service, and then the health consultation is performed according to the appointment time.

An embodiment of an IPTV end consultation system based on intelligent interaction disclosed in the present application is described in detail below with reference to fig. 2. As shown in fig. 2, the system disclosed in the present embodiment includes:

the health detection device is used for acquiring body health index information of the user;

the intelligent interaction equipment is used for acquiring a user voice signal, converting the voice signal into text information and performing man-machine interaction with a user;

the cloud server is used for acquiring health index information and generating a customized health consultation result according to the health index information;

the set top box is used for realizing communication between the IPTV and the cloud server as well as between the IPTV and the intelligent interaction equipment;

and the IPTV is used for realizing the broadcasting and/or displaying of the interactive content and the consultation result.

In at least one embodiment, the cloud server comprises:

the category domain positioning module is used for positioning a health consultation category domain consulted by the user;

the health index acquisition module is used for acquiring health index information corresponding to the user according to the health consultation category domain;

and the result generating module is used for generating a customized health consultation result according to the health index information.

In at least one embodiment, the health indicator obtaining module includes:

the query statement calling unit is used for calling a query statement normal form based on the multi-round conversation model corresponding to the health consultation category domain;

the voice interaction unit is used for replacing key inquiry information of the inquiry statement paradigm with user expression and carrying out multi-round voice interaction based on the user expression;

and the health index generation unit is used for acquiring user input information based on the multiple rounds of voice interaction and performing variable assignment on the user input information to generate health index information.

In at least one embodiment, the method further comprises:

the IPTV interactive module is used for displaying the query sentence paradigm through IPTV and attaching corresponding reply options, and a user replies through human-computer interaction so as to determine the health index information;

the man-machine interaction mode comprises physical key interaction, voice interaction or touch interaction.

The division of the modules and units herein is only one division of logical functions, and other divisions may be possible in actual implementation, for example, a plurality of modules and/or units may be combined or integrated in another system. The modules and units described as separate parts may be physically separated or not. The components displayed as cells may or may not be physical cells, and may be located in a specific place or distributed in grid cells. Therefore, some or all of the units can be selected according to actual needs to implement the scheme of the embodiment.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.