Disease simulation method and device, electronic equipment and storage medium

Abstract

The application relates to the technical field of artificial intelligence, and particularly discloses a disease simulation method and device, electronic equipment and a storage medium, wherein the method comprises the following steps: obtaining pet information, historical feeding information of a pet to be diagnosed, and examination information of a current disease of the pet to be diagnosed; constructing a virtual pet according to the pet information, constructing a simulation model according to the diagnosis information and the historical feeding information, and simulating a disease process of the pet to be diagnosed; determining at least one candidate disease information according to the examination information; inputting the virtual pet and each candidate disease information in the at least one candidate disease information into the simulation model respectively for disease simulation processing, and obtaining at least one simulation result; determining a diagnosis probability of each simulation result in the at least one simulation result according to the examination information, wherein the diagnosis probability is used for identifying a probability that the current disease is disease information corresponding to the simulation result corresponding to the diagnosis probability; and sending each simulation result and the diagnosis probability of each simulation result to a diagnostic doctor.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, specifically to a disease simulation method, device, electronic device, and storage medium. Background Technology

[0002] Because pets cannot speak, they cannot proactively express their condition or feelings during diagnosis. Therefore, veterinarians often rely on information obtained through various assistive devices, supplemented by their own experience, to deduce the pet's symptoms. Although current assistive devices are highly accurate, many diseases still present with similar symptoms, leading to lower diagnostic accuracy. Summary of the Invention

[0003] To address the aforementioned problems in the prior art, this application provides a disease simulation method, apparatus, electronic device, and storage medium, which can simulate candidate diseases by constructing virtual pets, thereby improving the accuracy of disease diagnosis.

[0004] In a first aspect, embodiments of this application provide a disease simulation method, the method comprising:

[0005] Obtain pet information, historical feeding information, and examination information of the current disease of the pet to be diagnosed;

[0006] A virtual pet is built based on pet information, and a simulation model is built based on diagnostic information and historical feeding information in order to simulate the disease process of the pet to be diagnosed.

[0007] At least one candidate disease information was identified based on the examination information;

[0008] The virtual pet and each candidate disease information from at least one candidate disease information are input into the simulation model for disease simulation processing to obtain at least one simulation result, wherein at least one simulation result corresponds one-to-one with at least one candidate disease information.

[0009] Based on the examination information, determine the diagnostic probability of each simulation result in at least one simulation result, wherein the diagnostic probability is used to identify the probability of the current disease being the disease information corresponding to the simulation result with the diagnostic probability.

[0010] Each simulation result and its probability of confirmation are sent to the diagnostic physician to assist them in making a diagnosis.

[0011] Secondly, embodiments of this application provide a disease simulation device, comprising:

[0012] The acquisition module is used to acquire pet information, historical feeding information, and examination information of the current disease of the pet to be diagnosed.

[0013] The modeling module is used to build a virtual pet based on pet information and a simulation model based on diagnostic information and historical feeding information, so as to simulate the disease process of the pet to be diagnosed.

[0014] The simulation module is used to determine at least one candidate disease information based on the examination information, and input the virtual pet and each candidate disease information from the at least one candidate disease information into the simulation model for disease simulation processing to obtain at least one simulation result, wherein at least one simulation result corresponds one-to-one with at least one candidate disease information;

[0015] The analysis module is used to determine the diagnostic probability of each simulation result in at least one simulation result based on the examination information. The diagnostic probability is used to identify the probability of the current disease being the disease information corresponding to the simulation result with the diagnostic probability.

[0016] The sending module is used to send each simulation result and the probability of diagnosis for each simulation result to the diagnostic physician to assist the physician in making a diagnosis.

[0017] Thirdly, embodiments of this application provide an electronic device, including: a processor connected to a memory for storing a computer program, and the processor for executing the computer program stored in the memory to cause the electronic device to perform the method as described in the first aspect.

[0018] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that causes a computer to perform the method as described in the first aspect.

[0019] Fifthly, embodiments of this application provide a computer program product, the computer program product including a non-transitory computer-readable storage medium storing a computer program, and a computer operable to perform the method as described in the first aspect.

[0020] Implementing the embodiments of this application has the following beneficial effects:

[0021] In this embodiment, the following steps are first taken: acquiring pet information, historical feeding information, and examination information of the pet's current illness; then, constructing a virtual pet identical to the pet based on the pet information; and building a simulation model simulating the pet's experience during its illness based on the diagnostic information and historical feeding information. Next, identifying at least one candidate disease that suggests the pet's current symptoms based on the examination information; and inputting the virtual pet and each candidate disease into the simulation model for disease simulation processing to obtain at least one simulation result. Finally, determining the diagnostic probability of each simulation result based on the examination information, where the diagnostic probability identifies the probability that the current disease corresponds to the disease information in the simulation result corresponding to the diagnostic probability. Finally, sending each simulation result and its diagnostic probability to the diagnosing physician to assist in diagnosis. Therefore, by using diagnostic information from assistive devices to determine the suspected disease and duration of illness in the pet to be diagnosed, and then extracting the pet's historical feeding information within that time period based on the duration of illness, a simulation model is constructed to simulate the pet's experience during the illness. The suspected disease is then simulated, and the probability of diagnosis is determined based on the similarity between the simulation results and the actual examination information. This probability of diagnosis is then simultaneously displayed to the diagnosing physician to assist in the diagnosis and improve the accuracy of the diagnosis. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 A schematic diagram of the hardware structure of a disease simulation device provided for an embodiment of this application;

[0024] Figure 2 A system framework diagram of a disease simulation method for recommending treatment plans for pets, provided for the implementation of this application;

[0025] Figure 3 A flowchart illustrating a disease simulation method provided for an embodiment of this application;

[0026] Figure 4 A schematic diagram illustrating how to determine the time period of illness of a pet to be diagnosed based on diagnostic information, as provided in this application embodiment;

[0027] Figure 5A schematic diagram illustrating the acquisition of fused disease features based on examination information, provided for an embodiment of this application;

[0028] Figure 6 A schematic diagram illustrating a typesetting result provided for an embodiment of this application;

[0029] Figure 7 A functional module block diagram of a disease simulation device provided for embodiments of this application;

[0030] Figure 8 This is a schematic diagram of the structure of an electronic device provided for an embodiment of this application. Detailed Implementation

[0031] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] The terms "first," "second," "third," and "fourth," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0033] In this document, the term "implementation" means that a specific feature, result, or characteristic described in connection with an implementation may be included in at least one implementation of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same implementation, nor is it a separate or alternative implementation mutually exclusive with other implementations. It will be explicitly and implicitly understood by those skilled in the art that the implementations described herein can be combined with other implementations.

[0034] First, refer to Figure 1 , Figure 1 This is a schematic diagram of the hardware structure of a disease simulation device provided in an embodiment of this application. The disease simulation device 100 includes at least one processor 101, a communication line 102, a memory 103, and at least one communication interface 104.

[0035] In this embodiment, the processor 101 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application.

[0036] Communication line 102 may include a path for transmitting information between the aforementioned components.

[0037] The communication interface 104 can be any transceiver-like device (such as an antenna) used to communicate with other devices or communication networks, such as Ethernet, RAN, wireless local area networks (WLAN), etc.

[0038] The memory 103 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0039] In this embodiment, the memory 103 can exist independently and be connected to the processor 101 via the communication line 102. Alternatively, the memory 103 can be integrated with the processor 101. The memory 103 provided in this embodiment is typically non-volatile. The memory 103 stores computer execution instructions for implementing the scheme of this application, and its execution is controlled by the processor 101. The processor 101 executes the computer execution instructions stored in the memory 103 to implement the method provided in the following embodiments of this application.

[0040] In an optional implementation, the computer execution instructions may also be referred to as application code, and this application does not specifically limit this.

[0041] In an optional implementation, processor 101 may include one or more CPUs, for example... Figure 1 CPU0 and CPU1 in the CPU.

[0042] In an optional implementation, the disease simulation device 100 may include multiple processors, such as... Figure 1 Processors 101 and 107 are shown in the diagram. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor here may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0043] In optional embodiments, if the disease simulation device 100 is a server, for example, it can be a standalone server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. Then the disease simulation device 100 may further include an output device 105 and an input device 106. The output device 105 communicates with the processor 101 and can display information in various ways. For example, the output device 105 can be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector, etc. The input device 106 communicates with the processor 101 and can receive user input in various ways. For example, the input device 106 can be a mouse, keyboard, touch screen device, or sensor device, etc.

[0044] The disease simulation device 100 described above can be a general-purpose device or a special-purpose device. The embodiments of this application do not limit the type of disease simulation device 100.

[0045] Secondly, it should be noted that the simulation method provided in this application can be applied to various planned simulation scenarios such as pet disease simulation, breeding simulation, and training simulation. In this embodiment, the simulation method provided in this application will be described using the pet disease simulation scenario as an example. The simulation methods in other scenarios are similar to those in the pet disease simulation scenario, and will not be described in detail here.

[0046] at last, Figure 2This application provides a system framework diagram for a disease simulation method in a scenario of simulating pet diseases. Specifically, the system may include: a user device 201, a physician device 202, a simulation device 203, and a database 204. The user device 201 and physician device 202 may be smartphones (such as Android phones, iOS phones, Windows Phones, etc.), tablets, PDAs, laptops, mobile internet devices (MIDs), etc. The user device 201 is used to acquire pet information and historical feeding information of the pet to be treated and send it to the simulation device 203; the physician device 202 is used to acquire examination information of the current disease of the pet to be diagnosed and send it to the simulation device 203, while simultaneously receiving and displaying the simulation results and diagnosis probability returned by the simulation device 203. The simulation device 203 can be a server, used to receive pet information and historical feeding information sent by the user device 201, and examination information sent by the veterinarian device 202. It then retrieves data from the database 204 based on the received information to construct a virtual pet and simulation model. Simultaneously, it identifies suspected diseases based on the examination information and performs disease simulations based on the virtual pet and simulation model. The simulation device 203 also analyzes the simulation results, determines the probability of diagnosis for each simulation result, and sends the simulation results and the probability of diagnosis to the veterinarian device 202 for display. Furthermore, the simulation device 203 updates and maintains the database 204.

[0047] Specifically, in this embodiment, the pet owner can log in to the disease simulation system on the user device 201 using the diagnosis number, fill in and upload pet information and historical feeding information, while the diagnosing veterinarian can log in to the disease simulation system via the veterinarian device 202, query the auxiliary instruments using the diagnosis number, and obtain the examination information of the pet's current disease. After obtaining this information, the user device 201 and the veterinarian device 202 respectively send it to the simulation device 203 for disease simulation processing.

[0048] Specifically, after acquiring the aforementioned information, the simulation device 203 will match several suspected diseases in the database 204 based on the examination information. Simultaneously, based on pet information, historical feeding information, and examination information, and combined with model data in the database 204, it will construct a virtual pet identical to the pet to be diagnosed in a healthy state, as well as a simulation model simulating the pet's experience during illness. Then, using the virtual pet and the simulation model, it will perform disease simulations on the identified suspected diseases, obtaining simulation results for each suspected disease. Next, based on the examination information, it will determine the probability of diagnosis for each suspected disease corresponding to the simulation result, and send these simulation results and diagnosis probabilities to the physician device 202 for display.

[0049] In this embodiment, the suspected disease of the pet to be diagnosed is determined by the diagnostic information of the auxiliary device. Then, a simulation model and virtual pet simulating the pet's experience during the illness are constructed by combining the pet's information and historical feeding information. The suspected disease is simulated, and the probability of diagnosis is determined based on the similarity between the simulation results and the actual examination information. This probability of diagnosis is then displayed to the diagnosing physician to assist in the diagnosis and improve the accuracy of the diagnosis.

[0050] The following will use a scenario of simulating pet diseases as an example to illustrate the disease simulation method disclosed in this application:

[0051] See Figure 3 , Figure 3 This is a flowchart illustrating a disease simulation method provided for an embodiment of this application. The disease simulation method includes the following steps:

[0052] 301: Obtain pet information, historical feeding information, and examination information of the current disease of the pet to be diagnosed.

[0053] In this embodiment, pet information may include: breed information, age information, body size information, weight information, appearance information, etc. Specifically, an application related to disease simulation can be installed on the user device 201, and then the user can log in to the disease simulation system by registering and logging in. The user then enters the diagnosis number to access the associated information entry interface and submits the information. Specifically, breed information and age information can be selected by clicking the secondary menu button after the text box; weight information can be directly entered as text; body size information and appearance information can be uploaded as multiple full-body images from different perspectives. Simultaneously, historical feeding information can be manually entered by the owner recalling the situation, or it can be a surveillance video of the feeding environment. When the historical feeding information is a surveillance video, it can also be uploaded to the disease simulation system as a file.

[0054] In an optional implementation, the breeder can also access a WeChat mini-program or official account associated with the disease simulation, log in via WeChat with real-name authentication, and then fill in the diagnosis number to access the associated information entry interface and submit it. Alternatively, they can access the disease simulation system's website, fill in the diagnosis number, and then access the associated information entry interface to submit it.

[0055] In this embodiment, the examination information may include information generated by various auxiliary devices after examining the pet to be diagnosed. The diagnosing physician can obtain this information by installing an application associated with the disease simulation on the physician device 202 and then querying the relevant examination information using the diagnosis number. Similarly, the diagnosing physician can also access a WeChat mini-program or official account associated with the disease simulation, log in via WeChat with real-name authentication, and then enter the diagnosis number to obtain the associated examination information. Alternatively, the diagnosing physician can access the disease simulation system's website and then enter the diagnosis number to obtain the associated examination information.

[0056] 302: Construct a virtual pet based on pet information, and build a simulation model based on diagnostic information and historical feeding information.

[0057] In this embodiment, the pet's standard physical development status can be determined using breed and age information from the pet's information, and then a body model of the pet can be constructed using body shape and weight information. Finally, a corresponding appearance texture is created using appearance information to cover the body model, resulting in a virtual pet of the pet to be diagnosed.

[0058] Specifically, a body database can be obtained based on breed information, and then a standard body model can be retrieved from the database based on age information. In short, this standard body model is constructed based on the average physical condition that a pet of that breed can achieve under normal development at that age, including aspects such as muscle development, skeletal development, body proportions, and organ development. Then, the body model is adjusted using the actual size and weight information of the pet to be diagnosed. For example, the muscle distribution and bone strength of the standard body model can be adjusted based on the actual body dimensions and the pet's weight. Finally, an appearance texture map is constructed based on the appearance information and applied to the adjusted body model, ultimately creating a virtual pet that is identical to the pet to be diagnosed in its healthy state.

[0059] In this embodiment, the simulation model is used to simulate the experience of the pet being diagnosed during its illness. Based on this, historical feeding information during the pet's illness can be extracted, feeding events occurring during this period can be extracted, and a feeding event sequence can be obtained to construct the simulation model. Specifically, firstly, the illness period of the pet can be determined based on the diagnostic information. In other words, the duration of the pet's current symptoms is determined based on the examination information, and then the illness period of the pet is calculated. Then, historical feeding information is extracted based on the illness period to obtain the target feeding information. That is, a segment with the same date and duration as the illness period is extracted from the historical feeding information as the target feeding information. For example, such as... Figure 4As shown, the disease period determined by the diagnostic information is one week, and the current time is April 14, 2022. Therefore, a segment from April 8, 2022 to April 14, 2022 in the historical feeding information can be extracted as the target feeding information.

[0060] Then, feeding events are extracted from the target feeding information to obtain at least one feeding event. Specifically, for text-based target feeding information, the text information can be extracted by setting keywords to obtain the at least one feeding event. For video-based target feeding information, the entire video can be split by extracting keyframes to obtain at least one feeding event.

[0061] Finally, based on the occurrence time of at least one feeding event, the at least one feeding event is sorted in chronological order to obtain a feeding event sequence. A simulation model is then constructed based on the feeding event sequence so that feeding events corresponding to the feeding event sequence can be generated in the simulation model.

[0062] 303: Identify at least one candidate disease based on the examination information.

[0063] In this embodiment, feature extraction can be performed on the examination information to obtain at least one disease feature, and then the at least one disease feature can be vertically stitched together to obtain a fused disease feature. For example, such as... Figure 5 As shown, the examination information can be divided according to the body parts of the pet to be diagnosed, resulting in examination sub-information for each body part, such as: [Head; Sub-information 1], [Torso; Sub-information 2], [Forelimbs; Sub-information 3], [Hinden limbs; Sub-information 4], and [Internal organs; Sub-information 5]. Then, feature extraction is performed on each examination sub-information to obtain at least one disease feature, such as: [Head; Disease Feature 1], [Torso; Disease Feature 2], [Forelimbs; Disease Feature 3], [Hinden limbs; Disease Feature 4], and [Internal organs; Disease Feature 5]. Finally, these disease features are vertically concatenated in a preset order, such as: head, torso, forelimbs, hindlimbs, and internal organs, to obtain the fused disease feature.

[0064]

[0065] Then, the similarity between the fused disease features and the disease features of each disease information in the disease database is calculated to obtain at least one first similarity. Specifically, in this embodiment, the cosine value of the angle between the fused disease features and the disease features of each disease information in the disease database can be calculated by dot product, and this cosine value is used as the first similarity between the fused disease features and the disease features of each disease information in the disease database.

[0066] In this embodiment, the cosine value of the angle is used as the first similarity between the fused disease features and the disease features of each disease information in the disease database. Since the cosine value ranges from -1 to 1, it retains the property of being 1 when they are the same, 0 when they are orthogonal, and -1 when they are opposite in high dimensions. That is, the closer the cosine value is to 1, the closer the directions of the two features are, and the higher the similarity; the closer it is to -1, the more opposite their directions are, and the lower the similarity; close to 0, it indicates that the two features are nearly orthogonal, reflecting the relative differences in the directions of the two features. Therefore, using the cosine value as the similarity between the fused disease features and the disease features of each disease information in the disease database can accurately represent the degree of similarity between the fused disease features and the disease features of each disease information in the disease database.

[0067] Finally, at least one candidate disease can be determined in the disease information database based on a preset prediction threshold and at least one first similarity. Specifically, the first similarity corresponding to each candidate disease is greater than or equal to the prediction threshold.

[0068] 304: Input the virtual pet and each candidate disease information from at least one candidate disease information into the simulation model to perform disease simulation processing and obtain at least one simulation result.

[0069] In this embodiment, the at least one simulation result corresponds one-to-one with at least one candidate disease information. Specifically, a disease event sequence can first be generated based on each candidate disease information. This disease event sequence is used to identify the effects of the disease on the pet's body over time under normal conditions, i.e., typical feeding conditions, and the symptoms it causes. For example, for cats, in the first 1-3 days after catching a cold, the virus multiplies, with little impact on the pet's body, usually manifesting as sneezing, runny nose, and loss of appetite. In the following 4-7 days, the viral multiplication is higher, developing into a respiratory infection, leading to increased coughing frequency accompanied by phlegm in the throat, thick nasal discharge, dry heaving, expectoration, rapid breathing, hoarseness, wheezing, and other symptoms. Based on this, the disease event sequence for a cold is: {[1-3 days: viral multiplication, no significant effect], [4-7 days: continuous viral multiplication, inducing respiratory infection, increasing respiratory infection symptoms]}.

[0070] Next, the simulation duration of the disease simulation treatment is determined, and the number of simulations is determined based on the simulation duration. It should be noted that in this embodiment, the simulation duration is the duration to be simulated, not the actual time spent on the simulation treatment. In short, a simulation duration of 3 months means that this simulation treatment will simulate the impact of events occurring over 3 months on the pet, while the actual treatment time may only be a few minutes, or even less.

[0071] In this embodiment, the simulation duration can be directly adopted from the duration of the illness period determined in step 302. For example, if the illness period of the pet to be diagnosed is determined to be one week based on the examination information, the simulation duration can be directly set to one week. This achieves a seamless simulation of the real-world situation, improving the reliability of the simulation results.

[0072] In this embodiment, the number of simulations can be determined by the simulation duration and the preset processing time for each simulation. Specifically, the preset processing time, like the simulation duration, refers to the duration to be simulated in each simulation, not the actual time spent in each simulation. For example, if the processing duration is 24 hours, each simulation will simulate the impact of events occurring within 24 hours on the pet. For example, the quotient of the simulation duration and the preset processing time for each simulation can be used as the number of simulations. For instance, if the simulation duration is one week and the processing time is 24 hours, then the number of simulations is 7.

[0073] Then, based on the disease event sequence and the feeding event sequence, the virtual pet undergoes a series of simulation parameter adjustments to obtain the simulation results corresponding to each candidate disease. Specifically, in the i-th parameter adjustment process, the simulation time corresponding to the i-th parameter adjustment process is determined, where i is an integer greater than or equal to 1. Then, based on the simulation time, the first disease event A is determined in the disease event sequence. i And determine the first feeding event B in the feeding event sequence based on the simulation time. i Subsequently, based on the first disease event A i And the first breeding incident B i For simulated virtual pet C i Adjusting the parameters yields the adjusted virtual pet D. i Where, when i=1, the simulated virtual pet C i For virtual pets. Finally, adjust virtual pet D. i The simulated virtual pet C in the (i+1)th parameter adjustment process i+1 The parameter adjustment process is performed for the (i+1)th time until the parameter adjustment process is performed for the simulation time, and then the simulation results corresponding to each candidate disease information are obtained.

[0074] In short, each parameter adjustment process determines the simulation date based on the number of times the parameter adjustment has been performed. For example, in a simulation lasting one week (April 8th-14th, 2022), with a processing time of 24 hours and seven simulations, the third parameter adjustment corresponds to the third day, April 10th, 2022. Based on this date, the first disease event and the first feeding event under that date can be determined from the disease event sequence and the feeding event sequence. Then, the impact of these events on the parameters of the simulated virtual pet corresponding to this parameter adjustment can be calculated, thus enabling the adjustment of the simulated virtual pet's parameters.

[0075] Finally, by combining the simulation results corresponding to each candidate disease information, at least one simulation result can be obtained.

[0076] 305: Determine the probability of diagnosis for each simulation result in at least one simulation result based on the examination information.

[0077] In this embodiment, the diagnostic probability is used to identify the probability that the current disease corresponds to the disease information of the simulated result corresponding to the diagnostic probability. Specifically, each simulated result can be processed for diagnosis to obtain at least one simulated diagnostic information. This diagnostic processing is the same as the diagnostic processing performed on the pet to be diagnosed. In short, the same examination and processing as previously performed on the pet to be diagnosed is performed on each simulated result. Then, the similarity between the diagnostic information and each of the at least one simulated diagnostic information is calculated to obtain at least one second similarity. The calculation method of the second similarity is similar to the calculation method of the first similarity in step 303, and will not be repeated here. Finally, the second similarity corresponding to each simulated result can be used as the diagnostic probability of each simulated result.

[0078] 306: Send each simulation result and the probability of diagnosis for each simulation result to the diagnostic physician to assist the physician in making a diagnosis.

[0079] In this embodiment, the device model information of the diagnostic physician's display device can first be obtained. This device model information may include: device type, such as mobile phone, tablet computer, personal computer, etc., and specific model. Therefore, the display size of the display device and its supported display modes can be determined based on the device model information. Then, at least one simulation result can be arranged according to the display size and the diagnostic probability of each simulation result to obtain the layout result. Specifically, taking a mobile phone as an example, its supported display mode is portrait display, then as follows... Figure 6As shown, all simulation results can be arranged vertically, with their corresponding probability of diagnosis added after each result. The simulation result with the highest probability of diagnosis is placed first and occupies the largest display space. The remaining simulation results are arranged in order of decreasing probability, with the second and third highest probabilities each occupying the second and third largest display spaces, respectively. Finally, the layout is sent to a display device for viewing by the diagnosing physician.

[0080] In summary, the disease simulation method provided by this invention first acquires the pet information, historical feeding information, and examination information of the pet's current disease. Then, a virtual pet identical to the pet to be diagnosed is constructed based on the pet information. A simulation model simulating the pet's experience during its illness is then constructed based on the diagnostic information and historical feeding information. Next, at least one candidate disease is identified based on the examination information, suggesting the pet's current symptoms. The virtual pet and each candidate disease are then input into the simulation model for disease simulation processing, yielding at least one simulation result. Finally, the diagnostic probability of each simulation result is determined based on the examination information, where the diagnostic probability identifies the probability that the current disease corresponds to the simulated result with the diagnostic probability. Each simulation result and its diagnostic probability are then sent to the diagnosing physician to assist in diagnosis. Therefore, by using diagnostic information from assistive devices to determine the suspected disease and duration of illness in the pet to be diagnosed, and then extracting the pet's historical feeding information within that time period based on the duration of illness, a simulation model is constructed to simulate the pet's experience during the illness. The suspected disease is then simulated, and the probability of diagnosis is determined based on the similarity between the simulation results and the actual examination information. This probability of diagnosis is then simultaneously displayed to the diagnosing physician to assist in the diagnosis and improve the accuracy of the diagnosis.

[0081] See Figure 7 , Figure 7 This is a functional module block diagram of a disease simulation device provided for an embodiment of this application. For example... Figure 7 As shown, the disease simulation device 700 includes:

[0082] The acquisition module 701 is used to acquire pet information, historical feeding information, and examination information of the current disease of the pet to be diagnosed.

[0083] Modeling module 702 is used to build a virtual pet based on pet information and to build a simulation model based on diagnostic information and historical feeding information in order to simulate the disease process of the pet to be diagnosed.

[0084] The simulation module 703 is used to determine at least one candidate disease information based on the examination information, and input the virtual pet and each candidate disease information in the at least one candidate disease information into the simulation model for disease simulation processing to obtain at least one simulation result, wherein the at least one simulation result corresponds one-to-one with at least one candidate disease information;

[0085] Analysis module 704 is used to determine the diagnostic probability of each simulation result in at least one simulation result based on the examination information, wherein the diagnostic probability is used to identify the probability of the current disease being the disease information corresponding to the simulation result with the diagnostic probability.

[0086] The sending module 705 is used to send each simulation result and the probability of diagnosis for each simulation result to the diagnostic physician to assist the diagnostic physician in making a diagnosis.

[0087] In an embodiment of the present invention, in constructing a simulation model based on diagnostic information and historical feeding information, the modeling module 702 is specifically used for:

[0088] Based on the diagnostic information, determine the time period of illness in the pet to be diagnosed;

[0089] Based on the time period of illness, historical feeding information is extracted to obtain the target feeding information;

[0090] Extract feeding events from the target feeding information to obtain at least one feeding event;

[0091] Based on the occurrence time of at least one feeding event, sort at least one feeding event to obtain a feeding event sequence;

[0092] A simulation model is constructed based on the sequence of feeding events, so that feeding events corresponding to the sequence of feeding events can be generated in the simulation model.

[0093] In an embodiment of the present invention, in terms of inputting a virtual pet and each candidate disease information from at least one candidate disease information into a simulation model for disease simulation processing to obtain at least one simulation result, the simulation module 703 is specifically used for:

[0094] Generate a disease event sequence based on each candidate disease information;

[0095] Determine the simulation duration for the disease simulation treatment, and determine the number of simulations based on the simulation duration;

[0096] Based on the disease event sequence and the feeding event sequence, the virtual pet simulation was performed a number of times and the parameters were adjusted to obtain the simulation results corresponding to each candidate disease information.

[0097] The simulation results corresponding to each candidate disease information are aggregated to obtain at least one simulation result.

[0098] In an embodiment of the present invention, in adjusting the simulation parameters of the virtual pet based on the disease event sequence and the feeding event sequence to obtain the simulation result corresponding to each candidate disease information, the simulation module 703 is specifically used for:

[0099] In the i-th parameter adjustment process, the simulation time corresponding to the i-th parameter adjustment process is determined, where i is an integer greater than or equal to 1;

[0100] The first disease event A is determined from the disease event sequence based on the simulation time. i And determine the first feeding event B in the feeding event sequence based on the simulation time. i ;

[0101] According to the first disease event A i And the first breeding incident B i For simulated virtual pet C i Adjusting the parameters yields the adjusted virtual pet D. i Where, when i=1, the simulated virtual pet C i For virtual pets;

[0102] Adjustments will be made to the virtual pet D. i The simulated virtual pet C in the (i+1)th parameter adjustment process i+1 The parameter adjustment process is performed for the (i+1)th time until the parameter adjustment process is performed for the simulation time, and then the simulation results corresponding to each candidate disease information are obtained.

[0103] In an embodiment of the present invention, in determining at least one candidate disease information based on examination information, the simulation module 703 is specifically used for:

[0104] Feature extraction is performed on the examination information to obtain at least one disease characteristic;

[0105] At least one disease feature is vertically spliced ​​together to obtain a fused disease feature;

[0106] Calculate the similarity between the fused disease characteristics and the disease characteristics of each disease in the disease information database, and obtain at least one first similarity;

[0107] Based on a preset prediction threshold and at least one first similarity, at least one candidate disease information is determined in the disease information database, wherein the first similarity corresponding to each candidate disease information is greater than or equal to the prediction threshold.

[0108] In an embodiment of the present invention, in determining the diagnostic probability of each simulation result in at least one simulation result based on examination information, the analysis module 704 is specifically configured to:

[0109] Each simulation result is processed for diagnosis to obtain at least one simulation diagnostic message;

[0110] Calculate the similarity between the diagnostic information and each of the at least one simulated diagnostic information to obtain at least one second similarity, wherein the at least one second similarity corresponds one-to-one with the at least one simulated diagnostic information;

[0111] The second similarity corresponding to each simulation result is used as the diagnostic probability of each simulation result.

[0112] In an embodiment of the present invention, in sending each simulation result and the probability of diagnosis for each simulation result to the diagnosing physician, the sending module 705 is specifically used for:

[0113] Obtain the device model information of the diagnostic physician's display device;

[0114] Determine the display size of the display device based on the device model information;

[0115] At least one simulation result is arranged according to the display size and the probability of diagnosis for each simulation result to obtain the layout result;

[0116] The layout results are sent to a display device for viewing by the diagnosing physician.

[0117] See Figure 8 , Figure 8 This is a schematic diagram of the structure of an electronic device provided for an embodiment of this application. For example... Figure 8 As shown, the electronic device 800 includes a transceiver 801, a processor 802, and a memory 803. These are connected via a bus 804. The memory 803 stores computer programs and data, and can transfer data stored in the memory 803 to the processor 802.

[0118] Processor 802 is used to read the computer program in memory 803 and perform the following operations:

[0119] Obtain pet information, historical feeding information, and examination information of the current disease of the pet to be diagnosed;

[0120] A virtual pet is built based on pet information, and a simulation model is built based on diagnostic information and historical feeding information in order to simulate the disease process of the pet to be diagnosed.

[0121] At least one candidate disease information was identified based on the examination information;

[0122] The virtual pet and each candidate disease information from at least one candidate disease information are input into the simulation model for disease simulation processing to obtain at least one simulation result, wherein at least one simulation result corresponds one-to-one with at least one candidate disease information.

[0123] Based on the examination information, determine the diagnostic probability of each simulation result in at least one simulation result, wherein the diagnostic probability is used to identify the probability of the current disease being the disease information corresponding to the simulation result with the diagnostic probability.

[0124] Each simulation result and its probability of confirmation are sent to the diagnostic physician to assist them in making a diagnosis.

[0125] In an embodiment of the present invention, in constructing a simulation model based on diagnostic information and historical feeding information, the processor 802 is specifically configured to perform the following operations:

[0126] Based on the diagnostic information, determine the time period of illness in the pet to be diagnosed;

[0127] Based on the time period of illness, historical feeding information is extracted to obtain the target feeding information;

[0128] Extract feeding events from the target feeding information to obtain at least one feeding event;

[0129] Based on the occurrence time of at least one feeding event, sort at least one feeding event to obtain a feeding event sequence;

[0130] A simulation model is constructed based on the sequence of feeding events, so that feeding events corresponding to the sequence of feeding events can be generated in the simulation model.

[0131] In an embodiment of the present invention, in inputting a virtual pet and each candidate disease information from at least one candidate disease information into a simulation model for disease simulation processing to obtain at least one simulation result, the processor 802 is specifically configured to perform the following operations:

[0132] Generate a disease event sequence based on each candidate disease information;

[0133] Determine the simulation duration for the disease simulation treatment, and determine the number of simulations based on the simulation duration;

[0134] Based on the disease event sequence and the feeding event sequence, the virtual pet simulation was performed a number of times and the parameters were adjusted to obtain the simulation results corresponding to each candidate disease information.

[0135] The simulation results corresponding to each candidate disease information are aggregated to obtain at least one simulation result.

[0136] In an embodiment of the present invention, in adjusting the simulation parameters of the virtual pet based on the disease event sequence and the feeding event sequence to obtain the simulation result corresponding to each candidate disease information, the processor 802 is specifically configured to perform the following operations:

[0137] In the i-th parameter adjustment process, the simulation time corresponding to the i-th parameter adjustment process is determined, where i is an integer greater than or equal to 1;

[0138] The first disease event A is determined from the disease event sequence based on the simulation time. i And determine the first feeding event B in the feeding event sequence based on the simulation time. i ;

[0139] According to the first disease event A i And the first breeding incident B i For simulated virtual pet C i Adjusting the parameters yields the adjusted virtual pet D. i Where, when i=1, the simulated virtual pet C i For virtual pets;

[0140] Adjustments will be made to the virtual pet D. i The simulated virtual pet C in the (i+1)th parameter adjustment process i+1 The parameter adjustment process is performed for the (i+1)th time until the parameter adjustment process is performed for the simulation time, and then the simulation results corresponding to each candidate disease information are obtained.

[0141] In an embodiment of the present invention, in determining at least one candidate disease information based on examination information, the processor 802 is specifically configured to perform the following operations:

[0142] Feature extraction is performed on the examination information to obtain at least one disease characteristic;

[0143] At least one disease feature is vertically spliced ​​together to obtain a fused disease feature;

[0144] Calculate the similarity between the fused disease characteristics and the disease characteristics of each disease in the disease information database, and obtain at least one first similarity;

[0145] Based on a preset prediction threshold and at least one first similarity, at least one candidate disease information is determined in the disease information database, wherein the first similarity corresponding to each candidate disease information is greater than or equal to the prediction threshold.

[0146] In an embodiment of the present invention, in determining the diagnostic probability of each simulation result in at least one simulation result based on examination information, the processor 802 is specifically configured to perform the following operations:

[0147] Each simulation result is processed for diagnosis to obtain at least one simulation diagnostic message;

[0148] Calculate the similarity between the diagnostic information and each of the at least one simulated diagnostic information to obtain at least one second similarity, wherein the at least one second similarity corresponds one-to-one with the at least one simulated diagnostic information;

[0149] The second similarity corresponding to each simulation result is used as the diagnostic probability of each simulation result.

[0150] In an embodiment of the present invention, in sending each simulation result and the probability of diagnosis for each simulation result to the diagnosing physician, the processor 802 is specifically configured to perform the following operations:

[0151] Obtain the device model information of the diagnostic physician's display device;

[0152] Determine the display size of the display device based on the device model information;

[0153] At least one simulation result is arranged according to the display size and the probability of diagnosis for each simulation result to obtain the layout result;

[0154] The layout results are sent to a display device for viewing by the diagnosing physician.

[0155] It should be understood that the disease simulation device in this application may include smartphones (such as Android phones, iOS phones, Windows Phones, etc.), tablet computers, PDAs, laptops, mobile internet devices (MIDs), robots, or wearable devices, etc. The above-mentioned disease simulation devices are merely examples and not exhaustive, and include, but are not limited to, the disease simulation devices described above. In practical applications, the above-mentioned disease simulation devices may also include: intelligent vehicle terminals, computer equipment, etc.

[0156] Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software combined with a hardware platform. Based on this understanding, all or part of the technical solution of the present invention that contributes to the background art can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

[0157] Therefore, embodiments of this application also provide a computer-readable storage medium storing a computer program that is executed by a processor to implement some or all of the steps of any of the disease simulation methods described in the above method embodiments. For example, the storage medium may include a hard disk, floppy disk, optical disk, magnetic tape, magnetic disk, USB flash drive, flash memory, etc.

[0158] This application also provides a computer program product comprising a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the disease simulation methods described in the above method embodiments.

[0159] It should be noted that, for the sake of simplicity, the aforementioned methods are described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are optional, and the actions and modules involved are not necessarily essential to this application.

[0160] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0161] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0162] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0163] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software program module.

[0164] If the integrated unit is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0165] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0166] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The above description of the embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A disease simulation method characterized by, The method comprises: acquiring pet information, historical feeding information of a pet to be diagnosed, and examination information of a current disease of the pet to be diagnosed; constructing a virtual pet according to the pet information, and constructing a simulation model according to the diagnosis information and the historical feeding information, so as to simulate a disease process of the pet to be diagnosed; determining at least one candidate disease information according to the examination information; inputting the virtual pet and each of the at least one candidate disease information into the simulation model respectively for disease simulation processing, to obtain at least one simulation result, wherein the at least one simulation result corresponds to the at least one candidate disease information one by one; determining a confirmed diagnosis probability of each simulation result in the at least one simulation result according to the examination information, wherein the confirmed diagnosis probability is used to identify a probability that the current disease is disease information corresponding to the simulation result corresponding to the confirmed diagnosis probability; sending the each simulation result and the confirmed diagnosis probability of the each simulation result to a diagnostic physician to assist the diagnostic physician in diagnosis; wherein the pet information comprises breed information, age information, body type information, weight information, and appearance information; the constructing a virtual pet according to the pet information comprises: determining a standard physical development state of the pet to be diagnosed through the breed information and the age information; constructing a body model of the pet to be diagnosed according to the standard physical development state and the body type information and the weight information; covering the body model by creating an appearance map through the appearance information to obtain the virtual pet; wherein the constructing a simulation model according to the diagnosis information and the historical feeding information comprises: determining a disease period of the pet to be diagnosed according to the diagnosis information; obtaining target feeding information by intercepting the historical feeding information according to the disease period; obtaining at least one feeding event by performing feeding event extraction on the target feeding information; obtaining a feeding event sequence by sorting the at least one feeding event according to occurrence time of the at least one feeding event; constructing the simulation model according to the feeding event sequence, so as to generate feeding events corresponding to the feeding event sequence in the simulation model through the feeding event sequence.

2. The method of claim 1, wherein, the inputting the virtual pet and each of the at least one candidate disease information into the simulation model respectively for disease simulation processing, to obtain at least one simulation result, comprises: generating a disease event sequence according to the each candidate disease information; determining a simulation duration of the disease simulation processing, and determining a simulation number according to the simulation duration; performing parameter adjustment processing on the virtual pet according to the disease event sequence and the feeding event sequence for the simulation number of times, to obtain a simulation result corresponding to the each candidate disease information; performing collection on the simulation result corresponding to the each candidate disease information, to obtain the at least one simulation result.

3. The method of claim 2, wherein, The simulation times parameter adjustment processing is performed on the virtual pet according to the disease event sequence and the feeding event sequence, and simulation results corresponding to each candidate disease information are obtained, and the simulation results include: In the i-th parameter adjustment processing, a simulation time corresponding to the i-th parameter adjustment processing is determined, where i is an integer greater than or equal to 1; determining a first disease event A in the sequence of disease events according to the simulation time i and determining a first feeding event B in the sequence of feeding events according to the simulation time i ; According to the first disease event A i and the first breeding event B i , the simulation virtual pet C i is parameter adjusted to obtain the adjusted virtual pet D i , wherein when i = 1, the simulation virtual pet C i is the virtual pet; adjusting the virtual pet D i as the simulation virtual pet C in the i+1th parameter adjustment process i+1 , the i+1th parameter adjustment process is performed until the simulation result corresponding to each candidate disease information is obtained after the simulation times of parameter adjustment processes are performed.

4. The method according to any one of claims 1 to 3, characterized in that, The at least one candidate disease information is determined according to the inspection information, and the method includes: Feature extraction is performed on the inspection information to obtain at least one disease feature; The at least one disease feature is vertically spliced to obtain a fused disease feature; Similarity degrees between the fused disease feature and disease features of each disease information in a disease information library are calculated to obtain at least one first similarity degree; According to a preset prediction threshold and the at least one first similarity degree, the at least one candidate disease information is determined in the disease information library, where a first similarity degree corresponding to each candidate disease information in the at least one candidate disease information is greater than or equal to the prediction threshold.

5. The method according to any one of claims 1 to 3, characterized in that, The diagnosis probability of each simulation result in the at least one simulation result is determined according to the inspection information, and the method includes: Diagnosis processing is performed on the each simulation result to obtain at least one simulation diagnosis information; Similarity degrees between the diagnosis information and each simulation diagnosis information in the at least one simulation diagnosis information are calculated to obtain at least one second similarity degree, where the at least one second similarity degree corresponds to the at least one simulation diagnosis information in one-to-one correspondence; The second similarity degree corresponding to the each simulation result is taken as the diagnosis probability of the each simulation result.

6. The method according to any one of claims 1 to 3, characterized in that, The each simulation result and the diagnosis probability of the each simulation result are sent to a diagnostic physician, and the method includes: Device model information of a display device of the diagnostic physician is acquired; A display size of the display device is determined according to the device model information; The at least one simulation result is typeset according to the display size and the diagnosis probability of the each simulation result to obtain a typesetting result; The typesetting result is sent to the display device for display, so that the diagnostic physician can view.

7. A disease simulation device, characterized by, The device includes: An acquisition module is configured to acquire pet information of a pet to be diagnosed, historical feeding information, and inspection information of a current disease of the pet to be diagnosed; A modeling module is configured to construct a virtual pet according to the pet information, and construct a simulation model according to the inspection information and the historical feeding information, so as to simulate a disease process of the pet to be diagnosed; A simulation module is configured to determine at least one candidate disease information according to the inspection information, and input the virtual pet and each candidate disease information in the at least one candidate disease information into the simulation model for disease simulation processing, to obtain at least one simulation result, where the at least one simulation result corresponds to the at least one candidate disease information in one-to-one correspondence; An analysis module is configured to determine a diagnosis probability of each simulation result in the at least one simulation result according to the inspection information, where the diagnosis probability is used to identify a probability that the current disease is a disease information corresponding to the simulation result corresponding to the diagnosis probability. The sending module is configured to send the each simulation result and the diagnosis probability of the each simulation result to a diagnostician to assist the diagnostician in diagnosis; The pet information includes breed information, age information, body type information, weight information, and appearance information; In the aspect of constructing the virtual pet according to the pet information, the modeling module is specifically configured to: Determine a body standard development state of the pet to be diagnosed according to the breed information and the age information; Construct a body model of the pet to be diagnosed according to the body standard development state and the body type information and the weight information; Overlay the body model with an appearance map created by the appearance information to obtain the virtual pet; In the aspect of constructing the simulation model according to the diagnosis information and the historical feeding information, the modeling module is specifically configured to: Determine a disease time period of the pet to be diagnosed according to the diagnosis information; Obtain target feeding information by intercepting the historical feeding information according to the disease time period; Obtain at least one feeding event by performing feeding event extraction on the target feeding information; Obtain a feeding event sequence by sorting the at least one feeding event according to the occurrence time of the at least one feeding event; Construct the simulation model according to the feeding event sequence, so that feeding events corresponding to the feeding event sequence are generated in the simulation model through the feeding event sequence.

8. An electronic device, comprising: A computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method of any one of claims 1-6.

9. A computer readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method of any one of claims 1-6.

Images