CN108109694B

CN108109694B - Event judging method and device, storage medium and electronic equipment

Info

Publication number: CN108109694B
Application number: CN201810009920.8A
Authority: CN
Inventors: 李向坤
Original assignee: Individual
Current assignee: Individual
Priority date: 2018-01-05
Filing date: 2018-01-05
Publication date: 2023-06-30
Anticipated expiration: 2038-01-05
Also published as: CN108109694A

Abstract

The disclosure relates to the technical field of artificial intelligence and computers, in particular to an event judging method and device based on brain mapping, a storage medium and electronic equipment. The method may include: constructing a plurality of boxes for mapping cerebral cortex columns; constructing a multi-layer pool according to the boxes for mapping brain function identification areas; constructing a library for mapping brain knowledge learning, updating and memorizing functions; providing a scheduling cloud for mapping brain prejudgement, scheduling coordination and external extension functions; and in response to a request for judging the event to be judged, scheduling at least one layer of pools in the multi-layer pools through the scheduling cloud to judge the event to be judged. The method and the device for judging the event to be judged provide a new mode for judging the event to be judged, so that the judging process of the event to be judged accords with the thinking of people, the accuracy of judging the event to be judged is improved, and the user experience is improved.

Description

Event judging method and device, storage medium and electronic equipment

Technical Field

The disclosure relates to the technical field of artificial intelligence and computers, in particular to an event judging method and device based on brain mapping, a storage medium and electronic equipment.

Background

Along with the rapid development of science and technology, artificial intelligence is increasingly applied to various industries so as to bring more convenience to daily life. For example, in the medical field, a patient's disease may be determined by an artificial intelligence physician.

Currently, the emerging artificial intelligence doctors require medical staff to inquire and collect basic information, symptom information, examination and other information of patients, and input the inquired information into the artificial intelligence doctors, and the artificial intelligence doctors output judgment results according to a judgment model constructed by a deep learning algorithm and based on the information input by the medical staff.

However, in the above manner, on one hand, the artificial intelligence doctor outputs the judging result according to the information of the medical staff inquiry, and the artificial intelligence doctor cannot inquire the patient autonomously or comprehensively, so that the cost is high, the efficiency is low, and especially for rural areas, mountain areas and pasture areas which lack medical staff resources, the existing artificial intelligence doctor cannot give more accurate judging result, and the user experience is poor; on the other hand, the judgment model constructed by the deep learning algorithm requires a large number of samples to train, and the judgment result output by the judgment model constructed by the deep learning algorithm is not high in accuracy or only single or few specific diseases can be accurately judged due to the limitation of training samples.

It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

It is an object of the present disclosure to provide a brain mapping-based event determination method and apparatus, a storage medium, and an electronic device, which overcome, at least in part, one or more of the problems due to the limitations and disadvantages of the related art.

According to one aspect of the present disclosure, there is provided an event determination method based on brain mapping, including:

constructing a plurality of boxes for mapping cerebral cortex columns;

constructing a multi-layer pool according to the boxes for mapping brain function identification areas;

constructing a library for mapping brain knowledge learning, updating and memorizing functions;

providing a scheduling cloud for mapping brain prejudgement, scheduling coordination and external extension functions;

and in response to a request for judging the event to be judged, scheduling at least one layer of pools in the multi-layer pools through the scheduling cloud to judge the event to be judged.

In one exemplary embodiment of the present disclosure, the constructing a plurality of boxes includes:

And defining boxes corresponding to the events according to the characteristic information of the events in the plurality of events in all dimensions.

In one exemplary embodiment of the present disclosure, the building a multi-layered pool from the plurality of boxes includes:

adding the plurality of boxes to each layer of the pool separately;

classifying the boxes in each layer of the pool according to classification characteristics of each layer of the pool.

In an exemplary embodiment of the present disclosure, the event to be determined is a disease determination event;

the scheduling, by the scheduling cloud, at least one of the multiple tiers of pools to determine the event to be determined in response to a request to determine the event to be determined includes:

responding to a request for judging an event to be judged, and acquiring a determined symptom set in the disease judgment event;

scheduling at least one of the multiple layers of the pools according to the determined set of symptoms;

screening the plurality of bins in the at least one layer of the pool according to the determined symptom set to obtain a first candidate bin;

screening the first candidate box according to the determined symptom set to obtain a second candidate box;

And judging the disease judgment event in the second candidate box according to the association information in the disease judgment event.

In an exemplary embodiment of the present disclosure, the screening the first candidate bin according to the determined symptom set to obtain a second candidate bin includes:

calculating a weight value for each of the first candidate bins using a bayesian formula and based on the set of determined symptoms;

and if the weight value of the first candidate box with the highest weight value is larger than a preset weight value, determining the first candidate boxes with the highest weight value and the front preset number of the first candidate boxes as the second candidate boxes.

calculating a weight value for each of the first candidate bins using a disease decision function and based on the set of determined symptoms;

In an exemplary embodiment of the present disclosure, the method further comprises:

if the weight value of the first candidate box with the highest weight value is not greater than a preset weight value, supplementing the determined symptom set;

screening the first candidate box according to the supplemented determined symptom set to obtain the second candidate box.

In an exemplary embodiment of the present disclosure, the supplementing the determined symptom set includes:

acquiring a disease symptom association table, wherein the disease symptom association table comprises a plurality of diseases and a plurality of symptoms, and each row comprises a symptom value of each symptom of the disease;

acquiring a first set of diseases including the determined set of symptoms based on the table of disease symptom associations and according to the determined set of symptoms;

if the first disease set is not empty, acquiring all the residual symptoms except the determined symptom set in all symptoms corresponding to all diseases in the first disease set, and marking the residual symptoms as a first symptom set;

adding the symptom values of each of the remaining symptoms in the first symptom set in the disease symptom association table;

Asking questions to the patient according to the residual symptoms with the maximum added symptom values, and acquiring answer information;

and if the answer information is affirmative, adding the residual symptom with the largest added symptom value to the determined symptom set to obtain the supplemented determined symptom set.

removing one symptom of the determined symptom set if the first disease set is empty, to obtain a reduced symptom set;

acquiring a second set of diseases comprising the reduced set of symptoms based on the table of disease symptom associations and according to the reduced set of symptoms;

if the second disease set is not empty, acquiring all the residual symptoms except for the reduced symptom set in all symptoms corresponding to all diseases in the second disease set, and marking the residual symptoms as a second symptom set;

calculating the association degree of each residual symptom in the second symptom set and the reduced symptom set by using a symptom association degree table;

sequencing the residual symptoms according to the sequence from big to small of the relevance, asking questions to the patient according to the residual symptoms in sequence according to the sequencing sequence, and obtaining answer information of the residual symptoms;

And if a preset number of continuous answer information in the answer information of each residual symptom is negative information, adding the residual symptoms corresponding to the answer information which is currently all positive information into the reduced symptom set to obtain the supplemented determined symptom set.

According to an aspect of the present disclosure, there is provided an event determination apparatus based on brain mapping, including:

a first construction module for constructing a plurality of bins for mapping cerebral cortex columns;

a second construction module for constructing a multi-layered pool from the plurality of boxes for mapping brain function recognition areas;

the third construction module is used for constructing a library and mapping the brain knowledge learning, updating and memory storage functions;

the providing module is used for providing a scheduling cloud and mapping brain prejudgement, scheduling coordination and external extension functions;

and the judging module is used for responding to the request of judging the event to be judged, and scheduling at least one layer of pools in the multi-layer pools through the scheduling cloud to judge the event to be judged.

According to one aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the brain mapping based event determination method of any one of the above.

According to one aspect of the present disclosure, there is provided an electronic device including:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the brain mapping based event decision method of any one of the above via execution of the executable instructions.

An event judging method and device based on brain mapping, a storage medium and an electronic device in the exemplary embodiments of the present disclosure, by constructing a plurality of boxes, multi-layer pools and libraries and providing a scheduling cloud to map working mechanisms and functions of brains through the plurality of boxes, multi-layer pools, libraries and the scheduling cloud, and scheduling at least one layer of pools in the multi-layer pools through the scheduling cloud to judge the event to be judged, on one hand, a new way of judging the event to be judged is provided according to the plurality of boxes, multi-layer pools and the scheduling cloud; on the other hand, compared with the prior art, a judgment model is not required to be built by a large number of data samples, and the judgment process of the event to be judged based on the boxes, the multi-layer pools and the scheduling clouds is more in line with the thinking of people through the working mechanism and the functions of the brain mapped by the boxes, the multi-layer pools and the scheduling clouds, so that the accuracy of judging the event to be judged is improved, and the user experience is improved; on the other hand, since the library is used for mapping the brain knowledge learning, updating and memorizing and storing functions, the accuracy of judging the transaction to be judged is further provided by updating and perfecting a plurality of boxes and a multi-layer pool in real time through the library.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The above and other features and advantages of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort. In the drawings:

FIG. 1 is a flow chart of an event decision method based on brain mapping of the present disclosure;

FIG. 2 is a flow chart of scheduling at least one tier pool of a multi-tier pool to determine events to be determined by scheduling clouds, as provided in an exemplary embodiment of the present disclosure;

FIG. 3 is a flow chart of acquiring a second candidate box provided in an exemplary embodiment of the present disclosure;

FIG. 4 is a flow chart of acquiring a second candidate box provided in another exemplary embodiment of the present disclosure;

FIG. 5 is a flow chart providing supplementation of a determined symptom set in an exemplary embodiment of the present disclosure;

FIG. 6 is a flowchart providing supplementation of a determined symptom set in another exemplary embodiment of the present disclosure;

FIG. 7 is a schematic diagram of the mapping of multiple boxes, multi-layer pools, libraries, and dispatch clouds on a computer provided in an exemplary embodiment of the present disclosure;

FIG. 8 is a block diagram of an event decision device based on brain mapping of the present disclosure;

FIG. 9 is a block diagram of an electronic device in an exemplary embodiment of the present disclosure;

fig. 10 is a schematic diagram of a program product in an exemplary embodiment of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the disclosed aspects may be practiced without one or more of the specific details, or with other methods, components, materials, devices, steps, etc. In other instances, well-known structures, methods, devices, implementations, materials, or operations are not shown or described in detail to avoid obscuring aspects of the disclosure.

The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, or in one or more software-hardened modules, or in different networks and/or processor devices and/or microcontroller devices.

The embodiment firstly discloses an event judging method based on brain mapping, which is applied to intelligent terminals and robots, wherein the intelligent terminals can be mobile phones, tablet computers, notebook computers, PDAs, televisions and other electronic devices. Referring to fig. 1, the event determination method based on brain mapping may include the steps of:

step S110, constructing a plurality of boxes for mapping cerebral cortex columns;

step S120, constructing a multi-layer pool according to the boxes for mapping brain function identification areas;

step S130, constructing a library for mapping brain knowledge learning, updating and memorizing functions;

step S140, providing a scheduling cloud for mapping brain prejudgement, scheduling coordination and external extension functions;

And step S150, responding to a request for judging the event to be judged, and scheduling at least one layer of pools in the multi-layer pools through the scheduling cloud to judge the event to be judged.

According to the event determination method based on brain mapping in the present exemplary embodiment, on one hand, determining an event to be determined according to a plurality of boxes, a multi-layer pool, and a scheduling cloud provides a new way of determining an event to be determined; on the other hand, compared with the prior art, a judgment model is not required to be built by a large number of data samples, and the judgment process of the event to be judged based on the boxes, the multi-layer pools and the scheduling clouds is more in line with the thinking of people through the working mechanism and the functions of the brain mapped by the boxes, the multi-layer pools and the scheduling clouds, so that the accuracy of judging the event to be judged is improved, and the user experience is improved; on the other hand, since the library is used for mapping the brain knowledge learning, updating and memorizing and storing functions, the accuracy of judging the transaction to be judged is further provided by updating and perfecting a plurality of boxes and a multi-layer pool in real time through the library.

Next, fig. 1 will be described further for the event determination method based on brain mapping in the present exemplary embodiment.

In step S110, a plurality of bins are constructed for mapping cerebral cortex columns.

In the present exemplary embodiment, the box is a mapping of a human cerebral cortex identifier on a computer, corresponding to a processing unit for an event. The cerebral cortex column is a basic unit of information processing, also called an identifier column, for identifying an event. Based on this, boxes corresponding to each of the events can be defined from the feature information of each of the events in all dimensions. The event may be, for example, a disease determination event, a service inquiry event, or the like, which is not particularly limited in the present exemplary embodiment. For example, when the event is a disease determination event, a box corresponding to each disease determination event, that is, one box corresponding to one disease, may be defined based on feature information of each disease in a plurality of diseases in all dimensions. In particular, the characteristic information of each disease in all dimensions may include: age, sex, weight, height, race, marital status, symptoms, signs, other factors, concomitant disorders, test results, etiology, differential diagnosis, and the like. From the above, it is known that boxes corresponding to each of the events are defined according to the feature information of each of the events in all dimensions, so that the boxes have the feature information of all dimensions of the event corresponding to the boxes, and thus the event corresponding to the boxes can be processed according to the boxes.

In step S120, a multi-layer pool is constructed from the plurality of boxes for mapping brain function recognition areas.

In the present exemplary embodiment, the pool is a mapping of human brain function identification regions on a computer corresponding to the processing of a set of events or a group of value information. When the event is a disease judgment event, the multi-layer pool can simulate the processes of human brain such as vision, outline, fuzzy recognition, emotion, 6 th feeling and the like to quickly, accurately and fuzzy recognize boxes by defining and identifying etiology, associated diseases, value groups and the like. Reflected in the computer system, i.e., for example: disease (box) such as virus, bacteria, protozoa is determined by etiology, typical symptoms, pathophysiological processes and the like.

Based on this, the constructing a multi-layered pool from the plurality of boxes may include: adding the plurality of boxes to each layer of the pool separately; classifying the boxes in each layer of the pool according to classification characteristics of each layer of the pool.

In the present exemplary embodiment, the number of layers of the multi-layered pool may be set by a developer, and the present exemplary embodiment is not particularly limited thereto. The classification characteristic of each layer of pool can be, for example, etiology, typical symptoms, pathophysiology, region and the like. It should be noted that the classification characteristic of each layer of pool is different. The process of constructing a multi-layered pool will be described taking an example in which an event is a disease judgment event and the number of layers of the pool is 3. First, a 3-layer pool is provided, and classification characteristics of the first layer pool to the third layer pool are gender, etiology and age, respectively. Then, a plurality of boxes are added to the first to third tanks, respectively. Finally, classifying the boxes in the first layer of pools according to gender, namely classifying the boxes into two types according to men and women respectively, wherein one type of boxes comprises boxes corresponding to diseases which women can suffer from, and the other type of boxes comprises boxes corresponding to diseases which men can suffer from; the boxes in the second floor are classified according to the etiology, and the boxes in the third floor are classified according to the ages.

In step S130, a library is constructed for mapping the brain knowledge learning, updating and memory storage functions.

In the present exemplary embodiment, the library is a mapping of brain knowledge learning, updating, memory storage function areas on a computer for simulating brain knowledge learning, updating, and storage functions. And updating and optimizing the boxes and the multi-layer pool according to the data in the library to improve the accuracy of event judgment.

In step S140, a scheduling cloud is provided for mapping brain prediction, scheduling coordination and external extension functions.

In the present exemplary embodiment, the scheduling cloud is a mapping of brain pre-judgment, scheduling coordination, and external extension functions on a computer. Is a central hub for mapping a brain working mechanism to process processes such as processing coordination, process control, output, external connection and the like of event judgment activities, and the main functions comprise: firstly, the scheduling operation of each functional area of the brain comprises variable flow direction, variable frequency, time and space, quantity, intervention intensity and the like of intervention of each functional module; secondly, process control is carried out, and process control is sent out by a next-stage functional module according to process acquired information analysis; thirdly, converting the uncertain result into a determined result, realizing a pre-judgment decision, and outputting and executing an instruction to send out; fourth, the hub connected with the outside (such as expert team, third party service, peripheral sensing equipment information processing, etc.); and fifthly, collecting storage information for background analysis, big data mining and online and offline learning.

In response to a request to determine an event to be determined, at least one of the multiple pools is scheduled by the scheduling cloud to determine the event to be determined in step S150.

In the present exemplary embodiment, in response to determining an event to be determined, feature information of the event to be determined is acquired, and at least one layer of pools in the multi-layer pool is scheduled by the scheduling cloud to determine the event to be determined.

From the above, the event to be determined is determined according to the boxes, the multi-layer pools and the scheduling cloud, and a new manner for determining the event to be determined is provided; in addition, compared with the prior art, a judgment model is not required to be built by a large number of data samples, and the working mechanism and the function of the brain are mapped by a plurality of boxes, a multi-layer pool and a scheduling cloud, so that the judgment process of the event to be judged based on the boxes, the multi-layer pool and the scheduling cloud is more in line with the thinking of people, the accuracy of judging the event to be judged is improved, and the user experience is improved; in addition, since the library is used for mapping brain knowledge learning, updating and memorizing functions, the library can update and perfect a plurality of boxes and a multi-layer pool in real time, and the accuracy of judging the transaction to be judged is further provided.

Next, the above-mentioned step S150 will be described by taking the event to be determined as a disease determination event as an example. As shown in fig. 2, the scheduling, by the scheduling cloud, at least one layer of the multi-layer pools to determine the event to be determined in response to the request to determine the event to be determined may include:

step S210, in response to the request for judging the event to be judged, acquiring the determined symptom set in the disease judgment event.

In the present exemplary embodiment, the user may send a request for determining the disease determination event to the smart terminal or the robot system through the interactive interface of the smart terminal or the robot. When the intelligent terminal or the robot receives the request for judging the disease judgment event, the intelligent terminal or the robot responds to the request for judging the disease judgment event and acquires a determined symptom set in the disease judgment event. The determined symptom set may include a plurality of symptom information, which may be, for example, sex, age, symptom, cause, induced symptom, etc., to which the present exemplary embodiment is not particularly limited.

Step S220, scheduling at least one layer of the pools in the multi-layer pool according to the determined symptom set.

In the present exemplary embodiment, each symptom in the determined symptom set is matched with the classification feature of each layer pool, and a pool in which the matching is successful is called. For example, when the determined set is "female, middle-aged, headache", if the multi-layered pool is two-layered, and the classification features of the two-layered pool are sex and age, respectively, the two-layered pool is called, and if the classification features of the two-layered pool are sex and etiology, respectively, only the pool whose classification feature is sex is called.

Step S230, screening the plurality of boxes in the at least one layer of the pool according to the determined symptom set to obtain a first candidate box.

In the present exemplary embodiment, for example, when the determined set is "female, middle-aged, headache", if the multi-layered pool is two-layered, and the classification features of the two-layered pool are sex and age, respectively, first, the two-layered pool is called, and a box corresponding to female is acquired in the pool whose classification feature is sex, while a box corresponding to middle-aged is acquired in the pool whose classification feature is age, then, an intersection of the box corresponding to female and the box corresponding to middle-aged is taken, and the intersection is determined as a first candidate box.

For another example, when the determined set is "female, middle-aged, headache", if the multi-layered pool is two-layered, and the classification features of the two-layered pool are sex and cause respectively, the pool with the classification feature of sex is called first, then the box corresponding to the female is taken from the pool with the classification feature of sex, and marked as the first candidate box.

Step S240, screening the first candidate box according to the determined symptom set to obtain a second candidate box.

In the present exemplary embodiment, the second candidate box may be acquired in the following two ways.

In a first aspect, as shown in fig. 3, the screening the first candidate box according to the determined symptom set to obtain a second candidate box may include:

step S310, calculating a weight value of each of the first candidate boxes based on the determined symptom set by using a bayesian formula.

In the present exemplary embodiment, first, the probability that the patient suffers from the disease corresponding to each first candidate bin is calculated from the determined symptom sets and the feature information of all dimensions of the disease corresponding to each first candidate bin, the patient is determined to suffer from the accuracy of the disease corresponding to each first candidate bin, and the patient not suffering from the disease corresponding to each first candidate bin is determined to suffer from the accuracy of the disease corresponding to each first candidate bin.

Based on this, the bayesian formula is:

wherein P is _i(Y|X) The weight value of the ith first candidate box is the probability that the patient is judged to be truly suffering from the disease corresponding to the first candidate box, P1 _i P2 for patient probability of suffering from disease corresponding to the ith first candidate box _i The accuracy of the disease for which the patient is determined to have the i first candidate box corresponds to P (X) is the probability of the patient being determined to have the disease for which the i first candidate box corresponds to;

P(X)＝P1 _i P2 _i +(1-P1 _i ) (1-P3 _i )

wherein P3 _i The patient who does not suffer from the disease corresponding to the ith first candidate box is determined to have no accuracy of the disease corresponding to the ith first candidate box.

The P is _i(Y|X) The value range of (2) is [0,1 ]]。

From the above, the weight value of each first candidate bin may be calculated from the determined symptom set.

Step S320, if the weight value of the first candidate box with the highest weight value is greater than a preset weight value, determining the first candidate box with the highest weight value and the preset number of the first candidate boxes as the second candidate box.

In the present exemplary embodiment, it is determined whether the weight value of the box with the highest weight value is greater than a preset weight value, and when the weight value of the box with the highest weight value is greater than the preset weight value, the plurality of first candidate boxes are sorted in the order from the large to the small weight value, and the preset number of first candidate boxes with the front sorting (i.e., the highest weight value) are obtained as the second candidate boxes. The preset weight value may be set by a developer, and the present exemplary embodiment is not particularly limited thereto. The preset number may be set by a developer, for example, may be 10 or 6, and the present exemplary embodiment is not limited thereto.

Mode two, the screening the first candidate bin according to the determined symptom set to obtain a second candidate bin may include: calculating a weight value for each of the first candidate bins using a disease decision function and based on the set of determined symptoms; and if the weight value of the first candidate box with the highest weight value is larger than a preset weight value, determining the first candidate boxes with the highest weight value and the front preset number of the first candidate boxes as the second candidate boxes.

In the present exemplary embodiment, the symptoms in the determined symptom set are classified to obtain an original symptom subset, an induced symptom subset, an examined symptom subset, and other symptom subsets. The other symptom subset includes all symptoms except the original symptom, the evoked symptom, and the check symptom.

The weight value of each first candidate bin is calculated from the original symptom subset, the evoked symptom subset, the check symptom subset, and the other symptom subset in combination with the disease decision function.

The disease determination function is:

where Wi is the weight value of the i first candidate bin, ωi is the weight of the original symptom subset relative to the i first candidate bins, ai is the contribution value of the other symptom subset relative to the i first candidate bins, bi is the contribution value of the induced symptom subset relative to the i first candidate bins, and Ci is the contribution value of the checked symptom subset relative to the i first candidate bins.

It should be noted that Ai may be calculated according to the number of other symptoms in other symptom subsets, bi may be calculated according to the number of induced symptoms in the symptom subsets, ci may be calculated according to the number of checked symptoms in the symptom subsets, ωi may be calculated based on a disease symptom weight table, and the process of calculating ωi based on a disease symptom weight table is as follows: finding the disease corresponding to the ith first candidate box in the disease symptom weight table, searching weights corresponding to all the original symptoms in the original symptom sub-set in all the symptoms corresponding to the disease, and adding the weights corresponding to all the original symptoms in the original symptom sub-set to obtain omega i. The disease symptom weight table will be described below, and thus will not be described here again.

In addition, if the weight value of the first candidate box with the highest weight value is greater than a preset weight value, the process of determining the first candidate box with the highest weight value and the previous preset number of the first candidate boxes as the second candidate box is the same as that of step S320, so that the description thereof is omitted here.

From the above, scheduling at least one of the pools in the multi-layered pool according to the set of determined symptoms and screening the plurality of bins in the at least one of the pools according to the set of determined symptoms to obtain a first candidate bin, and screening the first candidate bin according to the set of determined symptoms to obtain a second candidate bin, i.e., by initially screening the plurality of bins to obtain the first candidate bin and screening the second candidate on the basis of the first candidate bin, the amount of computation to screen the second candidate bin is reduced, providing screening efficiency.

Furthermore, as shown in fig. 4, the method may further include:

step S410, if the weight value of the first candidate box with the highest weight value is not greater than a preset weight value, supplementing the determined symptom set.

In this exemplary embodiment, the preset weight values have been described above, and thus are not described herein. As shown in fig. 5, the supplementing the determined symptom set may include:

step S510, a disease symptom association table is obtained, wherein the disease symptom association table comprises a plurality of diseases and a plurality of symptoms, and each row comprises a symptom value of each symptom of one disease.

In this exemplary embodiment, the disease symptom association table is established as follows:

the disease symptom weight table shown in table 1 below is first established.

TABLE 1

As can be seen from the above, the disease symptom weight table includes N symptoms and M diseases, and each row includes a weight value of each symptom corresponding to one disease.

The non-zero weight values in table 1 were modified to 1 to convert the disease symptom weight table to a disease symptom association table as shown in table 2.

As can be seen from the above, the disease symptom association table includes N symptoms and M diseases, and each row includes a symptom value of each symptom corresponding to one disease.

Step S520, based on the disease symptom association table and according to the determined symptom set, acquiring a first disease set comprising the determined symptom set.

In the present exemplary embodiment, it is determined whether or not a set of determined symptoms is included in all symptoms having a symptom value of 1 corresponding to each disease in table 2, and diseases including the set of determined symptoms are combined in all symptoms having a symptom value of 1 corresponding to the disease, to obtain a first disease set.

Step S530, if the first disease set is not empty, obtaining all the residual symptoms except the determined symptom set in all the symptoms corresponding to all the diseases in the first disease set, and marking the residual symptoms as a first symptom set;

in the present exemplary embodiment, when the first disease set is not empty, all symptoms of all diseases in the first disease set are combined to obtain a symptom set, all symptoms in the determined symptom set are removed from the symptom set, and all remaining symptoms are marked as the first symptom set. The first disease set is not empty, that is, the first disease set comprises at least one disease.

Step S540, adding the symptom values of the residual symptoms in the first symptom set in the disease symptom association table.

In the present exemplary embodiment, each remaining symptom in the first symptom set is searched in the sub-table in table 2, and all the symptom values in the column in which each remaining symptom is located in table 2 are added to obtain the symptom value after each remaining symptom is added.

Step S550, asking the question to the patient according to the residual symptom with the maximum added symptom value, and acquiring answer information.

In the present exemplary embodiment, the remaining symptoms are ordered in order of the added symptom value from large to small to obtain the remaining symptom with the largest added symptom value, and a question is asked to the patient according to the remaining symptom with the largest added symptom value, for example, when the remaining symptom with the largest added symptom value is headache, a question "you are headache? "and will" do you headache? "send to patient to obtain user answer information to the question.

Step S560, if the answer information is affirmative, adding the remaining symptom with the largest added symptom value to the determined symptom set to obtain the supplemented determined symptom set.

In the present exemplary embodiment, if the answer information is affirmative, the remaining symptom having the largest symptom value after addition is added to the determined symptom set to obtain a supplemented determined symptom set. The affirmative information is affirmative answer information to a question asking the patient according to the remaining symptoms.

If the symptom values of the two remaining symptoms after addition are the same and maximum, the degree of association between the two remaining symptoms and the set of determined symptoms is calculated, and a question is given to the patient according to the remaining symptom having the maximum degree of association. And when the answer information is affirmative, adding the residual symptom with the maximum association degree into the determined symptom set to obtain the supplemented determined symptom set. The calculation of the degree of association between the two remaining symptoms and the set of determined symptoms will be described below, and thus will not be described in detail here.

And if the answer information is negative information, asking a question to a user according to the residual symptoms which are arranged after the residual symptoms with the maximum added symptom values and are adjacent, and adding the residual symptoms which are arranged after the residual symptoms with the maximum added symptom values and are adjacent to the determined symptom set when the answer information is positive information, so as to obtain the supplemented determined symptom set.

Furthermore, as shown in fig. 6, the method may further include:

step S610, if the first disease set is empty, removing one symptom of the determined symptom set to obtain a reduced symptom set.

In the present exemplary embodiment, if the first set of diseases is empty, any one or a specified one of the set of determined symptoms is removed to obtain a reduced set of symptoms. It should be noted that the manner of removing one symptom in the determined symptom set is not limited to the above manner.

Step S620, obtaining a second disease set including the reduced symptom set based on the disease symptom association table and according to the reduced symptom set.

In the present exemplary embodiment, it is determined whether or not a reduced symptom set is included in all symptoms of which the symptom value is 1 corresponding to each disease in table 2, and diseases including the reduced symptom set in all symptoms of which the symptom value is 1 corresponding to the disease are combined to obtain a second disease set.

Step S630, if the second disease set is not empty, obtaining all the remaining symptoms except for the reduced symptom set in all the symptoms corresponding to all the diseases in the second disease set, and marking the remaining symptoms as a second symptom set.

In the present exemplary embodiment, when the second set of diseases is not empty, all symptoms of all diseases in the second set of diseases are combined to obtain a set of symptoms, all symptoms in the reduced set of symptoms are removed from the set of symptoms, and all remaining symptoms are marked as the second set of symptoms. The second disease set is not empty, namely the second disease set comprises at least one disease.

Step S640, calculating the association degree between each of the remaining symptoms in the second symptom set and the reduced symptom set by using a symptom association degree table.

In the present exemplary embodiment, the process of constructing the symptom association table is as follows:

the disease symptom association table shown in table 2 was converted to obtain the symptom disease association table shown in table 3.

TABLE 3 Table 3

Multiplying tables 2 and 3 and setting the degree of association of the same symptoms to 0 gave a symptom association table as described in table 4. Table 4 includes the degree of association between the symptoms.

TABLE 4 Table 4

Searching the association degree between each residual symptom in the second symptom set and each symptom in the reduced symptom set in the table 4, and adding the association degree between the same residual symptom and each symptom in the reduced symptom set to obtain the association degree between each residual symptom and the reduced symptom set. For example, the degree of association between the first residual symptom in the second symptom set and each symptom in the reduced symptom set is searched, the degree of association between the first residual symptom and each symptom in the reduced symptom set is obtained by adding the degree of association between the first residual symptom and each symptom in the reduced symptom set, and the degree of association between the first residual symptom and the reduced symptom set is calculated by repeating the steps.

Step 650, sorting the residual symptoms according to the order of the relevance from high to low, asking questions to the patient according to the residual symptoms in turn according to the sorting order, and obtaining answer information of the residual symptoms.

In the present exemplary embodiment, for example, the second symptom set includes 20 remaining symptoms, and the 20 remaining symptoms are ranked in order of the degree of association of the 20 remaining symptoms with the reduced symptom set from large to small. The patient is asked according to the sequencing order, namely, the patient is firstly asked according to the residual symptoms arranged at the first position, the answer information of the first residual symptoms is acquired, then the patient is asked according to the residual symptoms arranged at the second position, the answer information of the second residual symptoms is acquired, and the process is sequentially circulated to ask the patient according to the residual symptoms arranged at the second position.

Step S660, if a preset number of continuous answer information is negative information in the answer information of each of the remaining symptoms, adding the remaining symptoms corresponding to the answer information which is currently all positive information into the reduced symptom set, so as to obtain the supplemented determined symptom set.

In the present exemplary embodiment, the preset number may be set by a developer, for example, may be 10 or 20, which is not particularly limited in the present exemplary embodiment.

Step S660 is described with a preset number of 10. And when the patient is judged to have continuous 10 pieces of answer information which are all negative information in the answer information of the residual symptoms, stopping asking the question, and adding the residual symptoms corresponding to the answer information which is currently all positive information into a reduced symptom set to obtain the supplemented determined symptom set. Step S660 is described with reference to the example of step S650 and the preset number of steps being 10, when the patient is asked according to the above 20 remaining symptoms, if the answer information to the first 3 remaining symptoms is affirmative, and the answer information to the 4 th to 13 th remaining symptoms is negative, the question is stopped at this time, and the first 3 remaining symptoms are added to the reduced symptom set.

Step S420, screening the first candidate box according to the supplemented determined symptom set to obtain the second candidate box.

In the present exemplary embodiment, the principle of screening the plurality of first boxes according to the supplemented determined symptom sets to obtain the second candidate boxes is the same as that of the above-described step S310 and step S320, and thus will not be described herein.

According to the method, the determined symptom set is supplemented according to the mode of asking questions of the residual symptoms to the patient, and compared with the prior art, the method can autonomously ask questions of the patient to supplement symptoms, does not need intervention of doctors, and is good in user experience.

Step S250, determining the disease determination event in the second candidate box according to the associated information in the disease determination event.

In the present exemplary embodiment, the related information is induced symptom information, other symptom information, laboratory sheet information, image information (e.g., B-ultrasound, CT, etc.), etc., which are input by the user. Other symptom information may include, for example, whether the patient has an infectious disease, vaccinated, patient preference, patient occupation, familial genetic disease, etc., which is not particularly limited in the present exemplary embodiment.

The matching degree of each second candidate box can be calculated according to the related information and the feature information of all dimensions of the diseases corresponding to each second candidate box, and the disease corresponding to the second candidate box with the highest matching degree is determined as the disease corresponding to the disease judgment event, namely the disease suffered by the patient is the disease corresponding to the second candidate box with the highest matching degree.

It should be noted that, the disease corresponding to the first preset number of second candidate boxes with the highest matching degree may also be determined as the disease corresponding to the disease determination event, where the preset number may be 3 or 2, and the present exemplary embodiment is not limited thereto.

FIG. 7 shows a mapping schematic of multiple boxes, multi-layer pools, libraries, and dispatch clouds on a computer. In fig. 7, a patient 701 inputs original patient information to an application interface 703 of an intelligent terminal, the application interface 703 transmits the original patient information to an application background 702, the application background 702 analyzes the original patient information to generate diagnosis and treatment information, the diagnosis and treatment information is transmitted to a scheduling cloud 715, dialogue information is output to the application interface 703 through processing of the scheduling cloud 715, and the application interface 703 displays the dialogue information to the patient so that the patient interacts according to the dialogue information. The application interface 703 provides various forms of human-computer interaction, which is also a way to sense things, collect value information and learn.

The process of generating dialogue information by the scheduling cloud 715 according to the diagnosis and treatment information includes: the diagnostic information is transmitted to the preprocessing unit 704 such that the preprocessing unit 704 analyzes the diagnostic information to obtain critical diagnostic information and transmits the critical diagnostic information to the plurality of boxes, multi-layer pools and libraries 714, which generate critical questions based on the critical diagnostic information and transmit the critical questions to the output execution 706, which converts the critical questions to dialogue information. The preprocessing device 704 is essentially a central nervous system (cerebral cortex) of a human, and can grasp repetitive variation in the breadth direction, repetitive variation in the depth direction, repetitive variation in the time direction, namely memory variation and genetic variation through established artificial cerebral procedures, so as to perform memory-prediction-execution (output) on things to complete intelligent processes simulating human brain.

The plurality of boxes, multi-layer pools and libraries 714 may include: definition, identification 707 for defining a plurality of bins from the base data 711 and the accumulation data 712, wherein the accumulation data 712 can be updated from the collection of data for each patient; evolutionary learning 708 for learning feedback on the diagnostic accuracy of a patient to refine a plurality of bins and a multi-layer pool; time, breadth, depth, dimension 709 are used to build a multi-layered pool from multiple boxes, practice, cognition 710 is generated by analyzing time, breadth, depth, dimension 709 for rules representing brain mental activities.

The base data 711 and the accumulated data 712 represent libraries, definitions, logos 707, and evolutionary learning 708 form an intra-brain evolutionary network with mechanisms and basic conditions that enable evolution by order building of a layer network from underlying base data, thus forming an artificial brain decision 705, which can be considered as a human nervous system.

Note that, the implementation of all functions in the scheduling cloud 715 is based on cloud hardware and the cloud operating system 713. Cloud hardware and cloud operating system 713 form a material foundation for mapping the structures of various areas of the human brain.

It should be noted that although the steps of the methods of the present disclosure are illustrated in the accompanying drawings in a particular order, this does not require or imply that the steps must be performed in that particular order or that all of the illustrated steps be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.

In an exemplary embodiment of the present disclosure, there is also provided a brain mapping-based event determination apparatus, as shown in fig. 8, the brain mapping-based event determination apparatus 800 may include: a first building module 801, a second building module 802, a third building module 803, a providing module 804, and a determining module 805, wherein:

a first construction module 801, which may be used to construct a plurality of boxes, for mapping cerebral cortex columns;

a second construction module 802, which can be used to construct a multi-layer pool from the plurality of boxes, for mapping brain function recognition areas;

a third construction module 803, which can be used to construct a library for mapping brain knowledge learning, updating and memory storage functions;

a providing module 804, configured to provide a scheduling cloud for mapping brain prediction, scheduling coordination, and external expansion functions;

the determining module 805 may be configured to schedule, by the scheduling cloud, at least one tier pool of the multiple tiers of pools to determine an event to be determined in response to a request to determine the event to be determined.

The specific details of the event determination device module based on the brain map in the foregoing description have been described in detail in the corresponding event determination method based on the brain map, and thus will not be described herein.

It should be noted that although in the above detailed description several modules or units of a device for performing are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

Those skilled in the art will appreciate that the various aspects of the invention may be implemented as a system, method, or program product. Accordingly, aspects of the invention may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.

An electronic device 900 according to such an embodiment of the invention is described below with reference to fig. 9. The electronic device 900 shown in fig. 9 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.

As shown in fig. 9, the electronic device 900 is embodied in the form of a general purpose computing device. Components of electronic device 900 may include, but are not limited to: the at least one processing unit 910, the at least one storage unit 920, a bus 930 connecting the different system components (including the storage unit 920 and the processing unit 910), and a display unit 940.

Wherein the storage unit stores program code that is executable by the processing unit 910 such that the processing unit 910 performs steps according to various exemplary embodiments of the present invention described in the above-described "exemplary methods" section of the present specification. For example, the processing unit 910 may perform step S110 as shown in fig. 1, constructing a plurality of boxes for mapping cerebral cortex columns; step S120, constructing a multi-layer pool according to the boxes for mapping brain function identification areas; step S130, constructing a library for mapping brain knowledge learning, updating and memorizing functions; step S140, providing a scheduling cloud for mapping brain scheduling coordination and external extension functions; and step S150, responding to a request for judging the event to be judged, and scheduling at least one layer of pools in the multi-layer pools through the scheduling cloud to judge the event to be judged.

The storage unit 920 may include readable media in the form of volatile storage units, such as Random Access Memory (RAM) 9201 and/or cache memory 9202, and may further include Read Only Memory (ROM) 9203.

The storage unit 920 may also include a program/utility 9204 having a set (at least one) of program modules 9205, such program modules 9205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.

The bus 930 may be one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 900 may also communicate with one or more external devices 970 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 900, and/or any device (e.g., router, modem, etc.) that enables the electronic device 900 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 950. Also, electronic device 900 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 960. As shown, the network adapter 960 communicates with other modules of the electronic device 900 over the bus 930. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 900, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, a computer-readable storage medium having stored thereon a program product capable of implementing the method described above in the present specification is also provided. In some possible embodiments, the various aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the invention as described in the "exemplary methods" section of this specification, when said program product is run on the terminal device.

Referring to fig. 10, a program product 1000 for implementing the above-described method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

Furthermore, the above-described drawings are only schematic illustrations of processes included in the method according to the exemplary embodiment of the present invention, and are not intended to be limiting. It will be readily appreciated that the processes shown in the above figures do not indicate or limit the temporal order of these processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, for example, among a plurality of modules.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An event determination method based on brain mapping, comprising:

Constructing a plurality of boxes for mapping cerebral cortex columns;

in response to a request to determine an event to be determined, scheduling at least one layer of pools in the multi-layer pool by the scheduling cloud to determine the event to be determined, the event to be determined being a disease determination event, including: responding to a request for judging an event to be judged, and acquiring a determined symptom set in the disease judgment event;

screening the first candidate bin according to the determined symptom set to obtain a second candidate bin, comprising: calculating a weight value for each of the first candidate bins using a bayesian formula or a disease decision function and based on the set of determined symptoms; if the weight value of the first candidate box with the highest weight value is not greater than a preset weight value, supplementing the determined symptom set; screening the first candidate box according to the supplemented determined symptom set to obtain the second candidate box;

Determining the disease determination event in the second candidate bin according to the associated information in the disease determination event;

wherein said supplementing said set of determined symptoms comprises:

2. The brain mapping based event decision method according to claim 1, wherein said constructing a plurality of boxes comprises:

3. The brain mapping based event decision method according to claim 1, wherein said constructing a multi-layer pool from said plurality of boxes comprises:

adding the plurality of boxes to each layer of the pool separately;

4. The brain mapping based event decision method according to claim 1, wherein said screening said first candidate bin according to said determined set of symptoms to obtain a second candidate bin further comprises:

5. The brain mapping based event determination method according to claim 1, wherein said method further comprises:

6. An event determination apparatus based on brain mapping, comprising:

a determining module, configured to schedule, by the scheduling cloud, at least one layer of the multiple layers of pools to determine an event to be determined, where the event to be determined is a disease determining event, in response to a request to determine the event to be determined, including: responding to a request for judging an event to be judged, and acquiring a determined symptom set in the disease judgment event;

wherein said supplementing said set of determined symptoms comprises:

7. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the brain mapping based event decision method according to any one of claims 1 to 5.

8. An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the brain mapping based event decision method of any one of claims 1 to 5 via execution of the executable instructions.