Treatment plan recommendation method, device, electronic device and storage medium

Abstract

The present application relates to the field of artificial intelligence technology, and specifically discloses a treatment plan recommendation method, device, electronic device and storage medium, wherein the method comprises: constructing a virtual pet according to pet information and medical record information of a pet to be treated; matching at least one treatment plan in a treatment plan library according to the medical record information; performing simulated treatment on the virtual pet according to each treatment plan in at least one treatment plan, and obtaining at least one treatment result and at least one treatment log, wherein at least one treatment result corresponds to at least one treatment plan one-to-one, and at least one treatment log corresponds to at least one treatment plan one-to-one; determining at least one candidate treatment plan in at least one treatment plan according to the expected result and at least one treatment result; determining a target treatment plan in at least one candidate treatment plan according to the breeder's demand information and at least one treatment log; and recommending the target treatment plan to the breeder.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a treatment plan recommendation method, device, electronic device and storage medium. Background Art

[0002] As people's living standards improve, more and more families keep pets, and some families have already regarded pets as members of the family. However, due to life reasons, pet owners are usually unable to take care of their pets in time when they are out at work or taking their pets out for fun, which causes the pets to be injured or sick.

[0003] For some diseases, there are multiple treatment options. The effect, efficiency and cost of each treatment option are different, and the actual effect produced on different pets is also different. At present, we can only rely on the doctor's experience to choose one of the treatment options for trial. If the treatment effect is not good, try other treatment methods. This treatment method is not only inefficient, but also cannot guarantee whether the selected treatment method will cause sequelae to the pet or aggravate the pet's condition. Summary of the invention

[0004] In order to solve the above-mentioned problems existing in the prior art, the embodiments of the present application provide a treatment plan recommendation method, device, electronic device and storage medium, which can simulate the treatment effect of candidate treatment plans on pets before formal treatment, and recommend appropriate treatment plans to the breeder based on the treatment effect and the actual situation of the breeder. While improving the treatment efficiency, it can ensure that the selected treatment method will not cause sequelae to the pet.

[0005] In a first aspect, an embodiment of the present application provides a method for recommending a treatment plan, the method comprising:

[0006] According to the pet information and medical record information of the pet to be treated, a virtual pet is constructed to simulate the treatment process of the pet to be treated;

[0007] Matching at least one treatment plan in a treatment plan library according to the medical record information;

[0008] According to each treatment plan in at least one treatment plan, simulate treatment is performed on the virtual pet to obtain at least one treatment result and at least one treatment log, wherein the at least one treatment result corresponds to the at least one treatment plan one-to-one, and the at least one treatment log corresponds to the at least one treatment plan one-to-one;

[0009] determining at least one candidate treatment regimen among at least one treatment regimen based on the expected outcome and at least one treatment outcome;

[0010] determining a target treatment plan from at least one candidate treatment plan based on the breeder's demand information and at least one treatment log;

[0011] Recommend targeted treatment options to breeders.

[0012] In a second aspect, an embodiment of the present application provides a treatment plan recommendation device, comprising:

[0013] A construction module, used for constructing a virtual pet according to pet information and medical record information of the pet to be treated, so as to simulate the treatment process of the pet to be treated;

[0014] a simulation module, used to match at least one treatment plan in a treatment plan library according to the medical record information, and perform simulated treatment on the virtual pet according to each treatment plan in the at least one treatment plan to obtain at least one treatment result and at least one treatment log, wherein the at least one treatment result corresponds to the at least one treatment plan one-to-one, and the at least one treatment log corresponds to the at least one treatment plan one-to-one;

[0015] An analysis module, configured to determine at least one candidate treatment plan from at least one treatment plan based on the expected result and at least one treatment result, and to determine a target treatment plan from at least one candidate treatment plan based on the breeder's demand information and at least one treatment log;

[0016] The recommendation module is used to recommend the target treatment plan to the breeder.

[0017] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, the processor is connected to a memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device performs the method of the first aspect.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program enables a computer to execute the method of the first aspect.

[0019] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and is computer-operable to cause the computer to execute the method of the first aspect.

[0020] The implementation of the present application has the following beneficial effects:

[0021] In the embodiment of the present application, by obtaining the pet information and medical record information of the pet to be treated, a virtual pet identical to the pet raised by the breeder is constructed. And at least one treatment plan is matched in the treatment plan library according to the medical record information of the pet to be treated, so that according to each treatment plan in the at least one treatment plan, the virtual pet is simulated for treatment, and at least one treatment result and at least one treatment log are obtained. Then, at least one candidate treatment plan is determined in the at least one treatment plan according to the expected result expected by the breeder and at least one treatment result corresponding to the at least one treatment plan. And according to the breeder's demand information and at least one treatment log, the target treatment plan is determined in at least one candidate treatment plan, so as to recommend the target treatment plan to the breeder. Thus, before the formal treatment, by constructing a virtual pet identical to the pet raised by the breeder for simulated treatment, while realizing the prediction of the treatment effect of each treatment plan, the treatment effect of each treatment plan on the pet to be treated is visualized (treatment result) and digitized (treatment log). Then, based on the therapeutic effect of each treatment plan and the actual situation of the breeder, the appropriate treatment plan can be recommended to the breeder. While improving the treatment efficiency, it can ensure the feasibility of the selected treatment plan and that it will not cause sequelae to the pet. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the implementation modes of the present application, the drawings required for use in the description of the implementation modes will be briefly introduced below. Obviously, the drawings described below are some implementation modes of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 A schematic diagram of the hardware structure of a treatment plan recommendation device provided in an embodiment of the present application;

[0024] Figure 2 A system framework diagram of a treatment plan recommendation method in a scenario of recommending a treatment plan for a pet provided in an embodiment of the present application;

[0025] Figure 3 A schematic diagram of a treatment plan recommendation method provided in an embodiment of the present application;

[0026] Figure 4 A schematic diagram of an information filling interface of an application provided in an embodiment of the present application;

[0027] Figure 5 A schematic diagram of a medical record information uploading interface provided in an embodiment of the present application;

[0028] Figure 6A flowchart of a method for constructing a virtual pet based on pet information and medical history information of a pet to be treated provided in an embodiment of the present application;

[0029] Figure 7 A functional module composition block diagram of a treatment plan recommendation device provided in an embodiment of the present application;

[0030] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0032] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0033] Reference to "embodiment" herein means that a particular feature, result, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0034] First, see Figure 1 , Figure 1 The hardware structure diagram of a treatment plan recommendation device provided in an embodiment of the present application is as follows: The treatment plan recommendation 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 can be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application.

[0036] The communication link 102 may include a path to transmit information between the above components.

[0037] The communication interface 104 may be any transceiver-like device (eg, antenna, etc.) for communicating 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 types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0039] In this embodiment, the memory 103 can exist independently and be connected to the processor 101 via the communication line 102. The memory 103 can also be integrated with the processor 101. The memory 103 provided in the embodiment of the present application can generally be non-volatile. Among them, the memory 103 is used to store computer-executable instructions for executing the scheme of the present application, and the execution is controlled by the processor 101. The processor 101 is used to execute the computer-executable instructions stored in the memory 103, so as to implement the method provided in the following embodiment of the present application.

[0040] In an optional implementation, the computer-executable instructions may also be referred to as application code, which is not specifically limited in this application.

[0041] In an optional embodiment, the processor 101 may include one or more CPUs, such as Figure 1 CPU0 and CPU1 in.

[0042] In an optional embodiment, the treatment plan recommendation device 100 may include multiple processors, such as Figure 1 1 and 107. Each of these processors may be a single-CPU processor or a multi-CPU processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0043] In an optional embodiment, if the treatment plan recommendation device 100 is a server, for example, it can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. Then the treatment plan recommendation device 100 can also include an output device 105 and an input device 106. The output device 105 communicates with the processor 101 and can display information in a variety of 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. The input device 106 communicates with the processor 101 and can receive user input in a variety of ways. For example, the input device 106 can be a mouse, a keyboard, a touch screen device, or a sensor device.

[0044] The above-mentioned treatment plan recommendation device 100 can be a general device or a special device. The embodiment of the present application does not limit the type of the treatment plan recommendation device 100.

[0045] Secondly, it should be noted that the treatment plan recommendation method provided by the present application can be applied to scenarios where various plans such as treatment plans, training plans, and training plans for pets are recommended. In this embodiment, the treatment plan recommendation method provided by the present application will be described by taking the scenario of recommending a treatment plan for a pet as an example. The plan recommendation methods in other scenarios are similar to the plan recommendation methods in the scenario of recommending a treatment plan for a pet, and will not be described in detail here.

[0046] at last, Figure 2A system framework diagram of a treatment plan recommendation method in a scenario of recommending a treatment plan for a pet provided by an embodiment of the present application. Specifically, the system may include: a user device 201, a treatment simulation device 202, and a database 203. Among them, the user device 201 may be a smart phone (such as an Android phone, an iOS phone, a Windows Phone phone, etc.), a tablet computer, a PDA, a laptop computer, a mobile Internet device MID (Mobile Internet Devices, referred to as: MID), etc., which is used to obtain the pet information and medical record information of the pet to be treated, and send it to the treatment simulation device 202, and display the recommended treatment plan. The treatment simulation device 202 may be a server, which is used to receive the pet information and medical record information sent by the user device 201, and then retrieve the data in the database 203 according to the received information to construct a virtual pet and simulate the treatment. And analyze the simulation results, determine the recommended plan and feedback it to the user device 201. At the same time, the treatment simulation device 202 will also update and maintain the database 203.

[0047] In this embodiment, the breeder or pet doctor can log in to the treatment simulation system through the user device 201, fill in and upload the pet information, such as: the breed information, age information and multiple full-body images of the pet under different viewing angles. After receiving the pet information, the user device 201 can identify its identity, thereby connecting to the database 203 to obtain the medical record information of the pet, and matching all treatment plans in the database 203 according to the medical record information. In an optional embodiment, if the pet is receiving medical treatment in the current hospital for the first time, the information filling interface can also be displayed to the breeder, in which the breeder can fill in the hospital where the pet was previously treated, and authorize the current device to obtain the right to obtain the medical record information of the pet, so that the user device 201 can establish communication with the hospital system where the pet was previously treated to obtain the medical record information of the pet. After the user device 201 obtains the pet information and medical record information, it sends this information to the treatment simulation device 202, so that the treatment simulation device 202 analyzes this information, and at the same time calls the model data in the database 203 according to the analysis results to construct a simulated pet for simulated treatment. Then, the target treatment plan is determined by combining the simulation results of each treatment plan and the breeder's demand information, and the target treatment plan is returned to the user device 201.

[0048] In this embodiment, before formal treatment, a virtual pet identical to the pet raised by the owner is constructed for simulated treatment, and while predicting the treatment effect of each treatment plan, the treatment effect of each treatment plan on the pet to be treated is visualized (treatment results) and digitized (treatment log). Then, according to the treatment effect of each treatment plan and the actual situation of the owner, a suitable treatment plan can be recommended to the owner, which can improve the treatment efficiency while ensuring the feasibility of the selected treatment plan and will not cause sequelae to the pet.

[0049] The following will take the scenario of recommending a treatment plan for a pet as an example to illustrate the treatment plan recommendation method disclosed in this application:

[0050] See also Figure 3 , Figure 3 A flowchart of a treatment plan recommendation method provided in an embodiment of the present application. The treatment plan recommendation method includes the following steps:

[0051] 301: Construct a virtual pet based on the pet information and medical record information of the pet to be treated, so as to simulate the treatment process of the pet to be treated.

[0052] In this embodiment, the pet information may include: breed information, age information and full-body image. The pet information may be manually filled in or uploaded by the owner and input into the user device 201, and then sent by the user device 201 to the treatment simulation device 202 to construct a virtual pet. The medical record information may be obtained by the user device 201 after determining the identity information of the pet to be treated according to the pet information, and then matching the identity information in the medical record database.

[0053] At the same time, in this embodiment, the user device 201 can be a handheld mobile device of the breeder or veterinarian, such as a mobile phone, a PDA, etc.; or it can also be a fixed Internet device, such as a computer, a smart device with a display, etc. Based on this, when the user device 201 is a handheld mobile device, an application associated with the treatment plan recommendation can be installed in the handheld mobile device, and then the pet information can be filled in and submitted by registering and logging in; or the WeChat applet or public account associated with the treatment plan recommendation can be accessed, and then the real-name authenticated WeChat login method can be used to log in, thereby filling in and submitting the pet information. When the user device 201 is a fixed Internet device, the pet information can be filled in and submitted by visiting the website of the treatment plan recommendation and then registering and logging in. Specifically, if Figure 4As shown, taking the information filling interface of the application as an example, the breed information and age information can be selected by clicking the secondary menu button behind the text box to open the secondary menu, and the whole body image can be uploaded by clicking the file selection button to select the corresponding file. After the breeder fills in the information, he can submit the filled information to the treatment simulation device 202 by clicking the OK button. After receiving the information, the treatment simulation device 202 can start to analyze the information to build a corresponding model for subsequent simulation treatment.

[0054] In an optional implementation, the pet to be treated may be receiving medical treatment at the current hospital for the first time, and its medical record in the current hospital has not yet been established. The medical record information of the pet cannot be obtained by querying the database as described above. At this time, a new interface can be displayed to the owner again, such as Figure 5 As shown, the pet owner is requested to upload the medical records of the pet, or to provide the location of the medical records of the pet, such as the name of the hospital where the pet was previously treated, and obtain authorization. Thus, the user device 201 can access the hospital system corresponding to the hospital name, and obtain the medical records of the pet in the hospital where the pet was previously treated through the owner's authorization request.

[0055] In this embodiment, the medical record information may include: disease name, duration of illness and diagnosis data. Based on this, this embodiment provides a method for constructing a virtual pet based on the pet information and medical record information of the pet to be treated, such as Figure 6 As shown, the program includes:

[0056] 601: Obtain a corresponding body database according to the breed information, and obtain a standard body model in the body database according to the age information.

[0057] In this embodiment, the body database is used to store standard body models of pets of corresponding breeds at different age stages.

[0058] 602: Determine target disease characteristics in the historical medical record database according to the breed information, age information, disease name and disease duration.

[0059] In this embodiment, the target disease feature is used to identify physical changes that occur with a probability greater than a preset threshold after the disease. In short, the target disease feature is the physical change feature that occurs with a high probability after a certain type of pet suffers from a certain type of disease, including changes in body shape, muscle, internal organs, fat, bones, etc. Specifically, in this embodiment, at least one candidate medical record can be matched in the historical medical record library based on breed information, age information, disease name, and duration of illness, wherein the breed information, age information, disease name, and duration of illness of the sick pet corresponding to each candidate medical record in the at least one candidate medical record are the same as the breed information, age information, disease name, and duration of illness of the pet to be treated. Thus, feature extraction is performed on each candidate medical record to obtain at least one disease feature that corresponds one-to-one to at least one candidate medical record, and then feature convergence processing is performed on at least one disease feature to obtain the target disease feature.

[0060] In this embodiment, the convergence process is to perform probability statistics on each of the at least one disease feature obtained, find out the same and high-frequency parts of these disease features, and the disease features corresponding to this part can be considered as the accompanying features of the disease. Specifically, each disease feature can be composed of multiple indivisible sub-features, which are used to reflect all indivisible physical changes that occur on the body of the pet recorded in the candidate medical record corresponding to the disease feature during the illness period, that is, each sub-feature is used to identify the smallest indivisible feature or smallest physical change, each sub-feature corresponds to a physical change, and the feature content of any two sub-features is different.

[0061] Based on this, in this embodiment, first, by traversing the at least one disease feature, at least one sub-feature that is different from each other can be obtained. Then, based on the at least one disease feature, the number of occurrences of each sub-feature is determined again. Then, based on the number of occurrences of each sub-feature, the frequency of occurrence of each sub-feature is determined. Finally, based on the frequency of occurrence of each sub-feature and a preset frequency threshold, at least one target sub-feature is determined in the at least one sub-feature, specifically, the frequency of occurrence of each target sub-feature in the at least one target sub-feature is greater than or equal to the frequency threshold. Thus, a set of at least one target sub-feature can be used as a target disease feature.

[0062] 603: Adjust the target disease characteristic according to the diagnosis data to obtain an adjusted disease characteristic.

[0063] In this embodiment, the target disease characteristics are just some common characteristics of the disease. For different pets, due to a series of reasons such as physique, living environment, cause of illness, treatment during illness, etc., some unique physical changes may occur. Based on this, other characteristics that are different from the target disease characteristics can be determined according to the diagnostic data, and these characteristics can be added to the target disease characteristics. At the same time, the parameters of each sub-feature in the target disease characteristics can also be adjusted according to the diagnostic data, for example: the parameters of the body shape change sub-features are adjusted by the actual measured body shape data, the parameters of the bone change feature are adjusted by the X-ray data, etc., and then the adjustment of the target disease characteristics is completed to obtain the adjusted disease characteristics.

[0064] 604: Adjust the standard body model according to the adjusted disease characteristics to obtain a target body model.

[0065] In this embodiment, by adjusting each sub-feature in the disease feature, the changes in the pet's body when it is sick can be determined, and then the corresponding parts of the standard body model are adjusted according to these changes to obtain the target body model. Specifically, the sub-features of the left front leg muscles in the disease feature are adjusted as follows: muscle atrophy 10%, bone strength reduction 5%, and combined with the actual size data of the left front leg in the diagnostic data, the muscles, bones and external dimensions of the left front leg in the standard body model are adjusted.

[0066] 605: Extract features from the whole body image to obtain at least one appearance feature.

[0067] In this embodiment, the pet's body parts can be first divided, for example, the body can be divided into the head, trunk (back and abdomen), limbs (left forelimb, right forelimb, left hind limb and right hind limb) and tail (if any). Then, the appearance features of the divided areas are extracted separately to obtain the appearance features corresponding to each area. At the same time, the name of the part corresponding to each appearance feature is used as a part label and added to the appearance feature.

[0068] 606: Matching in a texture library according to at least one appearance feature to obtain at least one appearance texture.

[0069] In this embodiment, the at least one appearance map corresponds to at least one appearance feature. Specifically, the corresponding part map library can be obtained according to the part label of each appearance feature in the at least one appearance feature, wherein the part label is used to identify the part of the pet body corresponding to each appearance feature, and the part map library is used to store the map material of the corresponding part. Then, according to each appearance feature, matching is performed in the corresponding part map library to obtain the corresponding map material group. Finally, according to each appearance feature, a map generation process is performed on the map material group corresponding to each appearance feature to obtain at least one appearance map.

[0070] 607: Construct a virtual pet according to at least one appearance map and a target body model.

[0071] Based on the appearance map generation method described in step 606, in this embodiment, the appearance map can be overlaid on the position corresponding to the part label on the body model according to the part label of the appearance feature corresponding to each appearance map, and then a virtual pet can be constructed.

[0072] 302: Match at least one treatment plan in a treatment plan library according to the medical record information.

[0073] In this embodiment, all treatment plans can be matched in the treatment plan database according to the breed information in the pet information, the disease name and the duration of illness in the medical record information, as the at least one treatment plan.

[0074] 303: Perform simulated treatment on the virtual pet according to each treatment plan in at least one treatment plan, and obtain at least one treatment result and at least one treatment log.

[0075] In this embodiment, the at least one treatment result corresponds to at least one treatment plan, and similarly, the at least one treatment log also corresponds to at least one treatment plan. Specifically, a treatment event sequence can be generated according to each treatment plan, and the sequence includes several treatment events, and these treatment events are arranged in the order of the corresponding treatment plan. Then, starting from the first treatment event, the impact of the treatment event on the virtual pet is calculated, and then the physical data of the virtual pet is adjusted for the first time according to the impact, and then the impact of the second treatment event on the virtual pet after the first adjustment is calculated, and then the physical data of the virtual pet after the first adjustment is adjusted for the second time according to the impact, until all treatment events are calculated, and the final physical data of the virtual pet is obtained as the treatment result. At the same time, during the simulation process, the actual consumption time and actual consumption items of each treatment event can be recorded to obtain the treatment log of the treatment plan.

[0076] 304: Determine at least one candidate treatment plan from at least one treatment plan based on the expected result and at least one treatment result.

[0077] In this embodiment, feature extraction can be performed on the expected results to obtain at least one expected feature, and then matching is performed in each treatment result in at least one treatment result according to the at least one expected feature to obtain at least one group of matching results. Specifically, the at least one group of matching results corresponds to at least one treatment result one-to-one, and each group of matching results in at least one group of matching results contains at least one matching score, and at least one matching score corresponds to at least one expected feature one-to-one. Then, the treatment score of each treatment result can be determined according to at least one matching score in the matching results corresponding to each treatment result. Finally, according to the preset score threshold and the treatment score of each treatment result, at least one candidate treatment plan is determined in at least one treatment plan, wherein the treatment score of the treatment result corresponding to each candidate treatment plan in at least one candidate treatment plan is greater than or equal to the score threshold.

[0078] In this embodiment, the expected result is the owner's expectation of the treatment, for example, after the treatment is completed, what state the pet's body, bones, internal organs, etc. need to reach. Thus, by extracting features from these expectations, several corresponding expected features can be obtained. Then these expected features are matched with each treatment result, that is, the corresponding expected state after the simulated treatment is found in each treatment result. And the compliance rate of the state after the simulated treatment relative to the expected state is calculated, that is, how much the state after the simulated treatment reaches the expected state, as the matching score of the expected feature. Exemplarily, in the expected result, it is hoped that the visceral fat rate of the pet will be reduced by 10% after treatment, the visceral fat rate in treatment result 1 will be reduced by 8%, and the visceral fat rate in treatment result 2 will be reduced by 15%. Then the compliance rate of treatment result 1 in the expected feature of visceral fat rate is 80%, and the matching score of the expected feature of visceral fat rate in treatment result 1 is 80, and the compliance rate of treatment result 2 in the expected feature of visceral fat rate is 150%, and the matching score of the expected feature of visceral fat rate in treatment result 1 is 150.

[0079] In this embodiment, the treatment score of each treatment result can be obtained by performing a global sum according to the weight of the desired feature corresponding to each matching score according to at least one matching score corresponding to each treatment result. Exemplarily, the weight of each desired feature can be obtained by displaying the corresponding desired feature to the breeder and having the breeder assign the weight. Specifically, a list containing the at least one desired feature can be displayed to the breeder, and three options of high, medium and low can be provided behind each desired feature for the breeder to select and fill in. Thus, through the list of fill-in submitted by the breeder, the more important indicators in the eyes of the breeder can be determined, and then these important indicators can be assigned higher weights. For example: a weight of 3 is assigned to a desired feature with a high degree of importance, a weight of 2 is assigned to a desired feature with a medium degree of importance, and a weight of 1 is assigned to a desired feature with a low degree of importance.

[0080] 305: Determine a target treatment plan from at least one candidate treatment plan according to the breeder's demand information and at least one treatment log.

[0081] In this embodiment, the demand information may include: economic information, location expectation information and time expectation information, which respectively reflect the maximum expenditure that the owner can afford, the location where the pet is expected to receive treatment and the time required to complete the treatment. Based on this, in this embodiment, at least one first treatment plan can be first determined from at least one candidate treatment plan based on the location expectation information and the time expectation information. Specifically, the similarity between the location requirement information and the location expectation information of each first treatment plan in the at least one first treatment plan is greater than or equal to a first threshold, and the similarity between the time requirement information and the time expectation information of each first treatment plan is greater than or equal to a second threshold, that is, a batch of treatment plans whose treatment location and treatment duration meet the owner's needs.

[0082] Then, according to the treatment log of each first treatment plan, the expense information of each first treatment plan is determined. Then, according to the expense information and economic information of each first treatment plan, the expense score of each first treatment plan is determined. In this embodiment, the expense score can be expressed by formula ①:

[0083]

[0084] Wherein, y represents the cost score, x represents the value corresponding to the cost information of each first treatment plan, and a represents the value corresponding to the economic information.

[0085] Finally, a target treatment plan can be determined from at least one of the first treatment plans according to the cost score and treatment score of each first treatment plan. Specifically, the cost score and treatment score can be multiplied to obtain a final score, and then the treatment plan with a final score greater than the recommended score threshold is used as the target treatment plan.

[0086] 306: Recommend targeted treatment options to breeders.

[0087] In this embodiment, when there are multiple target treatment plans, they can be sorted according to the final score of each target treatment plan, and then recommended to the breeder in descending order of the final score.

[0088] In summary, in the treatment plan recommendation method provided by the present invention, by acquiring the pet information and medical record information of the pet to be treated, a virtual pet identical to the pet raised by the breeder is constructed. And at least one treatment plan is matched in the treatment plan library according to the medical record information of the pet to be treated, so that according to each treatment plan in the at least one treatment plan, the virtual pet is simulated for treatment to obtain at least one treatment result and at least one treatment log. Then, at least one candidate treatment plan is determined in the at least one treatment plan according to the expected result expected by the breeder and at least one treatment result corresponding to the at least one treatment plan. And according to the breeder's demand information and at least one treatment log, the target treatment plan is determined in at least one candidate treatment plan, so as to recommend the target treatment plan to the breeder. Thus, before the formal treatment, by constructing a virtual pet identical to the pet raised by the breeder for simulated treatment, while realizing the prediction of the treatment effect of each treatment plan, the treatment effect of each treatment plan on the pet to be treated is visualized (treatment result) and digitized (treatment log). Then, based on the therapeutic effect of each treatment plan and the actual situation of the breeder, the appropriate treatment plan can be recommended to the breeder. While improving the treatment efficiency, it can ensure the feasibility of the selected treatment plan and that it will not cause sequelae to the pet.

[0089] See also Figure 7 , Figure 7 This is a functional module block diagram of a treatment plan recommendation device provided in an embodiment of the present application. Figure 7 As shown, the treatment plan recommendation device 700 includes:

[0090] A construction module 701 is used to construct a virtual pet based on the pet information and medical record information of the pet to be treated, so as to simulate the treatment process of the pet to be treated;

[0091] The simulation module 702 is used to match at least one treatment plan in the treatment plan library according to the medical record information, and perform simulated treatment on the virtual pet according to each treatment plan in the at least one treatment plan to obtain at least one treatment result and at least one treatment log, wherein the at least one treatment result corresponds to the at least one treatment plan, and the at least one treatment log corresponds to the at least one treatment plan;

[0092] An analysis module 703 is used to determine at least one candidate treatment plan in at least one treatment plan according to the expected result and at least one treatment result, and to determine a target treatment plan in at least one candidate treatment plan according to the breeder's demand information and at least one treatment log;

[0093] The recommendation module 704 is used to recommend the target treatment plan to the breeder.

[0094] In the embodiment of the present invention, pet information may include: breed information, age information and full-body image; medical record information may include: disease name, duration of illness and diagnosis data. Based on this, in terms of constructing a virtual pet according to the pet information and medical record information of the pet to be treated, the construction module 701 is specifically used to:

[0095] Acquire a corresponding body database according to the breed information, and acquire a standard body model in the body database according to the age information, wherein the body database is used to store standard body models of pets of corresponding breeds at different age stages;

[0096] Determine the target disease feature in the historical medical record database according to the breed information, age information, disease name and duration of illness, wherein the target disease feature is used to identify physical changes with a probability greater than a preset threshold after the disease occurs;

[0097] Adjusting the target disease characteristic according to the diagnostic data to obtain an adjusted disease characteristic;

[0098] The standard body model is adjusted according to the adjusted disease characteristics to obtain a target body model;

[0099] Performing feature extraction on the whole body image to obtain at least one appearance feature;

[0100] Matching in a texture library according to at least one appearance feature to obtain at least one appearance texture, wherein at least one appearance texture corresponds to at least one appearance feature in a one-to-one manner;

[0101] A virtual pet is constructed based on at least one appearance map and a target body model.

[0102] In the embodiment of the present invention, in determining the target disease characteristics in the historical medical record library according to the variety information, age information, disease name and disease duration, the construction module 701 is specifically used to:

[0103] Matching at least one candidate medical record in the historical medical record database according to the breed information, age information, disease name and duration of illness, wherein the breed information, age information, disease name and duration of illness of the sick pet corresponding to each candidate medical record in the at least one candidate medical record are the same as the breed information, age information, disease name and duration of illness of the pet to be treated;

[0104] Extracting features from each candidate medical record to obtain at least one disease feature, wherein the at least one disease feature corresponds to the at least one candidate medical record in a one-to-one manner;

[0105] Perform feature convergence processing on at least one disease feature to obtain a target disease feature.

[0106] In the embodiment of the present invention, in performing feature convergence processing on at least one disease feature to obtain a target disease feature, the construction module 701 is specifically used to:

[0107] Traversing at least one disease feature to obtain at least one sub-feature, wherein each sub-feature of the at least one sub-feature is used to identify a minimum feature that cannot be further divided, and feature contents of any two sub-features are different;

[0108] According to at least one disease characteristic, determining the number of occurrences of each sub-characteristic;

[0109] According to the number of occurrences of each sub-feature, determine the occurrence frequency of each sub-feature;

[0110] Determining at least one target sub-feature from at least one sub-feature according to the occurrence frequency of each sub-feature and a preset frequency threshold, wherein the occurrence frequency of each target sub-feature in the at least one target sub-feature is greater than or equal to the frequency threshold;

[0111] A set of at least one target sub-feature is used as a target disease feature.

[0112] In an embodiment of the present invention, in determining at least one candidate treatment plan in at least one treatment plan according to the expected result and at least one treatment result, the analysis module 703 is specifically configured to:

[0113] Performing feature extraction on the expected result to obtain at least one expected feature;

[0114] According to the at least one desired feature, matching is performed in each treatment result of the at least one treatment result to obtain at least one group of matching results, wherein the at least one group of matching results corresponds one-to-one to the at least one treatment result, each group of matching results in the at least one group of matching results includes at least one matching score, and the at least one matching score corresponds one-to-one to the at least one desired feature;

[0115] Determine a treatment score for each treatment outcome according to at least one matching score in the matching results corresponding to each treatment outcome;

[0116] Based on a preset score threshold and the treatment score of each treatment outcome, at least one candidate treatment plan is determined in at least one treatment plan, wherein the treatment score of the treatment outcome corresponding to each candidate treatment plan in the at least one candidate treatment plan is greater than or equal to the score threshold.

[0117] In an embodiment of the present invention, the demand information may include: economic information, location expectation information and time expectation information. Based on this, in determining the target treatment plan from at least one candidate treatment plan according to the breeder's demand information and at least one treatment log, the analysis module 703 is specifically used to:

[0118] Determine at least one first treatment plan from at least one candidate treatment plan according to the location expectation information and the time expectation information, wherein the similarity between the location requirement information and the location expectation information of each first treatment plan in the at least one first treatment plan is greater than or equal to a first threshold, and the similarity between the time requirement information and the time expectation information of each first treatment plan is greater than or equal to a second threshold;

[0119] Determining the cost information of each first treatment plan according to the treatment log of each first treatment plan;

[0120] Determining a cost score for each first treatment plan based on the cost information and economic information of each first treatment plan;

[0121] A target treatment regimen is determined in at least one of the first treatment regimens based on the cost score and the treatment score of each of the first treatment regimens.

[0122] In the embodiment of the present invention, it can be expressed by formula ②:

[0123]

[0124] Wherein, y represents the cost score, x represents the value corresponding to the cost information of each first treatment plan, and a represents the value corresponding to the economic information.

[0125] See also Figure 8 , Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 8 As shown, the electronic device 800 includes a transceiver 801, a processor 802 and a memory 803. They are connected via a bus 804. The memory 803 is used to store computer programs and data, and can transmit the data stored in the memory 803 to the processor 802.

[0126] The processor 802 is used to read the computer program in the memory 803 and perform the following operations:

[0127] According to the pet information and medical record information of the pet to be treated, a virtual pet is constructed to simulate the treatment process of the pet to be treated;

[0128] Matching at least one treatment plan in a treatment plan library according to the medical record information;

[0129] According to each treatment plan in at least one treatment plan, simulate treatment is performed on the virtual pet to obtain at least one treatment result and at least one treatment log, wherein the at least one treatment result corresponds to the at least one treatment plan one-to-one, and the at least one treatment log corresponds to the at least one treatment plan one-to-one;

[0130] determining at least one candidate treatment regimen among at least one treatment regimen based on the expected outcome and at least one treatment outcome;

[0131] determining a target treatment plan from at least one candidate treatment plan based on the breeder's demand information and at least one treatment log;

[0132] Recommend targeted treatment options to breeders.

[0133] In an embodiment of the present invention, pet information may include: breed information, age information and full-body image; medical record information may include: disease name, duration of illness and diagnosis data. Based on this, in terms of constructing a virtual pet according to the pet information and medical record information of the pet to be treated, the processor 802 is specifically configured to perform the following operations:

[0134] Acquire a corresponding body database according to the breed information, and acquire a standard body model in the body database according to the age information, wherein the body database is used to store standard body models of pets of corresponding breeds at different age stages;

[0135] Determine the target disease feature in the historical medical record database according to the breed information, age information, disease name and duration of illness, wherein the target disease feature is used to identify physical changes with a probability greater than a preset threshold after the disease occurs;

[0136] Adjusting the target disease characteristic according to the diagnostic data to obtain an adjusted disease characteristic;

[0137] The standard body model is adjusted according to the adjusted disease characteristics to obtain a target body model;

[0138] Performing feature extraction on the whole body image to obtain at least one appearance feature;

[0139] Matching in a texture library according to at least one appearance feature to obtain at least one appearance texture, wherein at least one appearance texture corresponds to at least one appearance feature in a one-to-one manner;

[0140] A virtual pet is constructed based on at least one appearance map and a target body model.

[0141] In an embodiment of the present invention, in determining the target disease characteristics in the historical medical record library according to the variety information, age information, disease name and disease duration, the processor 802 is specifically configured to perform the following operations:

[0142] Matching at least one candidate medical record in the historical medical record database according to the breed information, age information, disease name and duration of illness, wherein the breed information, age information, disease name and duration of illness of the sick pet corresponding to each candidate medical record in the at least one candidate medical record are the same as the breed information, age information, disease name and duration of illness of the pet to be treated;

[0143] Extracting features from each candidate medical record to obtain at least one disease feature, wherein the at least one disease feature corresponds to the at least one candidate medical record in a one-to-one manner;

[0144] Perform feature convergence processing on at least one disease feature to obtain a target disease feature.

[0145] In an embodiment of the present invention, in performing feature convergence processing on at least one disease feature to obtain a target disease feature, the processor 802 is specifically configured to perform the following operations:

[0146] Traversing at least one disease feature to obtain at least one sub-feature, wherein each sub-feature of the at least one sub-feature is used to identify a minimum feature that cannot be further divided, and feature contents of any two sub-features are different;

[0147] According to at least one disease characteristic, determining the number of occurrences of each sub-characteristic;

[0148] According to the number of occurrences of each sub-feature, determine the occurrence frequency of each sub-feature;

[0149] Determining at least one target sub-feature from at least one sub-feature according to the occurrence frequency of each sub-feature and a preset frequency threshold, wherein the occurrence frequency of each target sub-feature in the at least one target sub-feature is greater than or equal to the frequency threshold;

[0150] A set of at least one target sub-feature is used as a target disease feature.

[0151] In an embodiment of the present invention, in determining at least one candidate treatment plan in at least one treatment plan according to the expected result and at least one treatment result, the processor 802 is specifically configured to perform the following operations:

[0152] Performing feature extraction on the expected result to obtain at least one expected feature;

[0153] According to the at least one desired feature, matching is performed in each treatment result of the at least one treatment result to obtain at least one group of matching results, wherein the at least one group of matching results corresponds one-to-one to the at least one treatment result, each group of matching results in the at least one group of matching results includes at least one matching score, and the at least one matching score corresponds one-to-one to the at least one desired feature;

[0154] Determine a treatment score for each treatment outcome according to at least one matching score in the matching results corresponding to each treatment outcome;

[0155] Based on a preset score threshold and the treatment score of each treatment outcome, at least one candidate treatment plan is determined in at least one treatment plan, wherein the treatment score of the treatment outcome corresponding to each candidate treatment plan in the at least one candidate treatment plan is greater than or equal to the score threshold.

[0156] In an embodiment of the present invention, the demand information may include: economic information, location expectation information and time expectation information. Based on this, in determining the target treatment plan from at least one candidate treatment plan according to the breeder's demand information and at least one treatment log, the processor 802 is specifically configured to perform the following operations:

[0157] Determine at least one first treatment plan from at least one candidate treatment plan according to the location expectation information and the time expectation information, wherein the similarity between the location requirement information and the location expectation information of each first treatment plan in the at least one first treatment plan is greater than or equal to a first threshold, and the similarity between the time requirement information and the time expectation information of each first treatment plan is greater than or equal to a second threshold;

[0158] Determining the cost information of each first treatment plan according to the treatment log of each first treatment plan;

[0159] Determining a cost score for each first treatment plan based on the cost information and economic information of each first treatment plan;

[0160] A target treatment regimen is determined in at least one of the first treatment regimens based on the cost score and the treatment score of each of the first treatment regimens.

[0161] In the embodiment of the present invention, it can be expressed by formula ③:

[0162]

[0163] Wherein, y represents the cost score, x represents the value corresponding to the cost information of each first treatment plan, and a represents the value corresponding to the economic information.

[0164] It should be understood that the treatment plan recommendation device in the present application may include a smart phone (such as an Android phone, an iOS phone, a Windows Phone phone, etc.), a tablet computer, a PDA, a laptop computer, a mobile Internet device MID (Mobile Internet Devices, referred to as: MID), a robot or a wearable device, etc. The above treatment plan recommendation device is only an example, not an exhaustive list, including but not limited to the above treatment plan recommendation device. In actual applications, the above treatment plan recommendation device may also include: a smart vehicle terminal, a computer device, etc.

[0165] Through the description of the above implementation modes, those skilled in the art can clearly understand that the present invention can be implemented by combining software with a hardware platform. Based on such an understanding, all or part of the contribution of the technical solution of the present invention to the background technology can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation modes of the present invention or some parts of the implementation modes.

[0166] Therefore, the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement some or all of the steps of any treatment plan recommendation method described in the above method implementation. For example, the storage medium may include a hard disk, a floppy disk, an optical disk, a tape, a disk, a USB flash drive, a flash memory, etc.

[0167] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the treatment plan recommendation methods described in the above method embodiments.

[0168] It should be noted that, for the sake of simplicity, the aforementioned method implementations are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the implementations described in the specification are all optional implementations, and the actions and modules involved are not necessarily required by the present application.

[0169] In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0170] In the several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device implementation described above is only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0171] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0172] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software program module.

[0173] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present 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, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0174] A person skilled in the art may understand that all or part of the steps in the various methods of the above-mentioned embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable memory, and the memory may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0175] The above is a detailed introduction to the implementation methods of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above implementation methods is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for recommending a treatment plan, characterized in that: The method comprises: Constructing a virtual pet according to pet information and medical record information of the pet to be treated so as to simulate the treatment process of the pet to be treated; Matching at least one treatment plan in the treatment plan library according to the medical record information; According to each treatment plan of the at least one treatment plan, the virtual pet is subjected to simulated treatment to obtain at least one treatment result and at least one treatment log, wherein the at least one treatment result corresponds to the at least one treatment plan one-to-one, and the at least one treatment log corresponds to the at least one treatment plan one-to-one; determining at least one candidate treatment regimen among the at least one treatment regimen based on the expected outcome and the at least one treatment outcome; determining a target treatment plan from the at least one candidate treatment plan according to the breeder's demand information and the at least one treatment log; recommending the target treatment regimen to the breeder; in, The pet information includes: breed information, age information and full-body image; The medical record information includes: disease name, duration of illness and diagnosis data; The step of constructing a virtual pet based on the pet information and medical record information of the pet to be treated includes: Acquire a corresponding body database according to the breed information, and acquire a standard body model in the body database according to the age information, wherein the body database is used to store standard body models of pets of corresponding breeds at different age stages; Determine a target disease feature in a historical medical record database according to the breed information, the age information, the disease name and the duration of illness, wherein the target disease feature is used to identify physical changes that have a probability of occurring after illness that is greater than a preset threshold; Adjusting the target disease characteristic according to the diagnostic data to obtain an adjusted disease characteristic; Adjusting the standard body model according to the adjusted disease characteristics to obtain a target body model; Performing feature extraction on the whole body image to obtain at least one appearance feature; Matching in a texture library according to the at least one appearance feature to obtain at least one appearance texture, wherein the at least one appearance texture corresponds to the at least one appearance feature in a one-to-one manner; The virtual pet is constructed according to the at least one appearance map and the target body model.

2. The method according to claim 1, characterized in that Determining target disease characteristics in a historical medical record database according to the variety information, the age information, the disease name and the duration of illness includes: Matching at least one candidate medical record in a historical medical record database according to the breed information, the age information, the disease name and the duration of illness, wherein the breed information, age information, disease name and duration of illness of the sick pet corresponding to each candidate medical record in the at least one candidate medical record are the same as the breed information, age information, disease name and duration of illness of the pet to be treated; Extracting features from each candidate medical record to obtain at least one disease feature, wherein the at least one disease feature corresponds to the at least one candidate medical record in a one-to-one manner; Perform feature convergence processing on the at least one disease feature to obtain a target disease feature.

3. The method according to claim 2, characterized in that The performing feature convergence processing on the at least one disease feature to obtain a target disease feature includes: Traversing the at least one disease feature to obtain at least one sub-feature, wherein each sub-feature of the at least one sub-feature is used to identify a minimum feature that cannot be further divided, and feature contents of any two sub-features are different; Determining the number of occurrences of each of the sub-features according to the at least one disease feature; Determine the occurrence frequency of each sub-feature according to the number of occurrences of each sub-feature; Determine at least one target sub-feature in the at least one sub-feature according to the occurrence frequency of each sub-feature and a preset frequency threshold, wherein the occurrence frequency of each target sub-feature in the at least one target sub-feature is greater than or equal to the frequency threshold; A set of the at least one target sub-feature is used as the target disease feature.

4. The method according to claim 1, characterized in that: Determining at least one candidate treatment plan from the at least one treatment plan according to the expected result and the at least one treatment result comprises: Performing feature extraction on the expected result to obtain at least one expected feature; According to the at least one desired feature, matching is performed in each treatment result of the at least one treatment result to obtain at least one group of matching results, wherein the at least one group of matching results corresponds to the at least one treatment result one-to-one, each group of matching results in the at least one group of matching results includes at least one matching score, and the at least one matching score corresponds to the at least one desired feature one-to-one; Determine a treatment score for each treatment result according to at least one matching score in the matching results corresponding to each treatment result; According to a preset score threshold and the treatment score of each treatment outcome, at least one candidate treatment plan is determined in the at least one treatment plan, wherein the treatment score of the treatment outcome corresponding to each candidate treatment plan in the at least one candidate treatment plan is greater than or equal to the score threshold.

5. The method according to claim 1, characterized in that The demand information includes: economic information, location expectation information and time expectation information; Determining a target treatment plan from the at least one candidate treatment plan based on the breeder's demand information and the at least one treatment log includes: Determine at least one first treatment plan from the at least one candidate treatment plan according to the location expectation information and the time expectation information, wherein the similarity between the location requirement information and the location expectation information of each first treatment plan in the at least one first treatment plan is greater than or equal to a first threshold, and the similarity between the time requirement information and the time expectation information of each first treatment plan is greater than or equal to a second threshold; Determining the expense information of each first treatment plan according to the treatment log of each first treatment plan; Determining a cost score of each first treatment plan according to the cost information of each first treatment plan and the economic information; The target treatment regimen is determined in the at least one first treatment regimen according to the cost score and the treatment score of each of the first treatment regimens.

6. The method according to claim 5, characterized in that The spending score satisfies the following formula: Wherein, y represents the cost score, x represents the value corresponding to the cost information of each first treatment plan, and a represents the value corresponding to the economic information.

7. A treatment plan recommendation device, characterized in that: The device comprises: A construction module, used to construct a virtual pet according to the pet information and medical record information of the pet to be treated, so as to simulate the treatment process of the pet to be treated; a simulation module, configured to match at least one treatment plan in the treatment plan library according to the medical record information, and perform simulated treatment on the virtual pet according to each treatment plan in the at least one treatment plan to obtain at least one treatment result and at least one treatment log, wherein the at least one treatment result corresponds to the at least one treatment plan in one-to-one correspondence, and the at least one treatment log corresponds to the at least one treatment plan in one-to-one correspondence; An analysis module, configured to determine at least one candidate treatment plan from among the at least one treatment plan according to the expected result and the at least one treatment result, and to determine a target treatment plan from among the at least one candidate treatment plan according to the breeder's demand information and the at least one treatment log; A recommendation module, used for recommending the target treatment plan to the breeder; in, The pet information includes: breed information, age information and full-body image; The medical record information includes: disease name, duration of illness and diagnosis data; In the aspect of constructing a virtual pet according to the pet information and medical history information of the pet to be treated, the construction module is specifically used for: Acquire a corresponding body database according to the breed information, and acquire a standard body model in the body database according to the age information, wherein the body database is used to store standard body models of pets of corresponding breeds at different age stages; Determine a target disease feature in a historical medical record database according to the breed information, the age information, the disease name and the duration of illness, wherein the target disease feature is used to identify physical changes that have a probability of occurring after illness that is greater than a preset threshold; Adjusting the target disease characteristic according to the diagnostic data to obtain an adjusted disease characteristic; Adjusting the standard body model according to the adjusted disease characteristics to obtain a target body model; Performing feature extraction on the whole body image to obtain at least one appearance feature; Matching in a texture library according to the at least one appearance feature to obtain at least one appearance texture, wherein the at least one appearance texture corresponds to the at least one appearance feature in a one-to-one manner; The virtual pet is constructed according to the at least one appearance map and the target body model.

8. An electronic device, characterized in that: The method comprises a processor, a memory, a communication interface and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the one or more programs include instructions for executing the steps in any one of the methods 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 according to any one of claims 1 to 6.

Images