Physical examination main examination conclusion generation method and device and computer program product

Abstract

The invention discloses a physical examination main examination conclusion generation method and device and a computer program product, and the method comprises the steps: obtaining physical examination data sent by a terminal, and determining initial conclusion structured data corresponding to the physical examination data based on a pre-trained large model; acquiring specified auxiliary information input by a user at the terminal from the terminal; and performing logical judgment on the initial conclusion structured data and the specified auxiliary information by utilizing a rule engine so as to output a main examination conclusion corresponding to the physical examination data. By combining the large model and the rule engine technology, the accuracy and processing efficiency of the physical examination conclusion are improved, and the defect that the manual main examination efficiency needs to be improved in the related technology is overcome.

Description

Technical Field

[0001] The present disclosure relates to the field of information processing technology, and in particular to a method and device for generating a physical examination conclusion, and a computer program product. Background Art

[0002] The main examination is a summary judgment and suggestion on the overall health status of the examinee made by the main examiner based on the results of all examination items after a comprehensive health examination.

[0003] The traditional inspection method relies on manual analysis and experience judgment, which has low work efficiency and is easily affected by subjective factors, resulting in inaccurate and subjective results. Summary of the invention

[0004] The main purpose of the present invention is to provide a method and device for generating a physical examination main examination conclusion, and a computer program product to solve the technical problems existing in the related technology.

[0005] In order to achieve the above-mentioned purpose, according to the first aspect of the present disclosure, a method for generating a main conclusion of a physical examination is provided, comprising: obtaining physical examination data sent by a terminal, and determining initial conclusion structured data corresponding to the physical examination data based on a pre-trained large model; obtaining designated auxiliary information input by a user at the terminal from the terminal; using a rule engine to perform logical judgment on the initial conclusion structured data and the designated auxiliary information to output a main examination conclusion corresponding to the physical examination data, wherein the input information, logical judgment conditions, and output information are configured in a visual configuration manner to form a rule of the rule engine; the logical judgment condition is defined as judging whether the value of the input information satisfies any condition, whether it satisfies part of the conditions, or whether it satisfies all the conditions; the output information is defined as diagnostic disease information, suspected disease information, or abnormal problem information; when configuring the rule of the rule engine, each input information is combined in a visual configuration manner, the combined input information is combined with different logical judgment conditions in a visual configuration manner to obtain a judgment combination, and the judgment combination is combined with different output information in a visual configuration manner to obtain the rule of the rule engine.

[0006] Optionally, using a rule engine to perform logical judgment on the initial conclusion structured data and designated auxiliary information includes: taking the initial conclusion structured data and designated auxiliary information as input to the rule engine; determining corresponding logical judgment conditions based on the input, and outputting a main inspection conclusion corresponding to the physical examination data according to the judgment logic of the logical judgment conditions; using the logical judgment conditions in the rule engine rules to perform logical judgment on the initial conclusion structured data and designated auxiliary information, wherein the main inspection conclusion includes diagnosed diseases, suspected diseases, and abnormal problems corresponding to the physical examination data.

[0007] Optionally, the method further includes: obtaining feedback suggestions for the main inspection conclusion; optimizing the rules of the rule engine based on the feedback suggestions, including: optimizing the input information, logical judgment conditions, and / or output information of the rules.

[0008] Optionally, when training the big model, physical examination data training samples are obtained, and the training samples are labeled to obtain department summary, examination findings, abnormal description, standard words, onset site, size, quantity, and grade; the department summary and examination findings are used as input of the big model, and the abnormal description, standard words, onset site, size, quantity, and grade are used as output of the big model to train the big model to obtain a pre-trained big model.

[0009] Optionally, the determining of the initial conclusion structured data corresponding to the physical examination data based on the pre-trained big model includes: determining the target abnormality description, target standard word, target onset site, target size, target quantity, and target level corresponding to the physical examination data based on the pre-trained big model.

[0010] Optionally, obtaining specified auxiliary information input by the user at the terminal includes: obtaining case information corresponding to the physical examination data, wherein the case information includes basic information, specific case information, and questionnaire data; obtaining auxiliary examination results corresponding to the physical examination data; obtaining judgment information on whether to perform an examination, and obtaining previous physical examination information.

[0011] According to a second aspect of the present disclosure, a device for generating a main conclusion of a physical examination is provided, comprising a large model calling unit, configured to obtain physical examination data sent by a terminal, and determine initial conclusion structured data corresponding to the physical examination data based on a pre-trained large model; an auxiliary information obtaining unit, configured to obtain designated auxiliary information input by a user at the terminal from the terminal; an output unit, configured to use a rule engine to perform logical judgment on the initial conclusion structured data and the designated auxiliary information to output a main conclusion corresponding to the physical examination data, wherein the input information, logical judgment conditions, and output information are configured in a visual configuration manner to form a rule of the rule engine; the logical judgment condition is defined as judging whether the value of the input information satisfies any condition, whether it satisfies some conditions, or whether it satisfies all conditions; the output information is defined as diagnostic disease information, suspected disease information, or abnormal problem information; when configuring the rule of the rule engine, each input information is combined in a visual configuration manner, the combined input information is combined with different logical judgment conditions in a visual configuration manner to obtain a judgment combination, and the judgment combination is combined with different output information in a visual configuration manner to obtain the rule of the rule engine.

[0012] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, storing computer instructions for causing the computer to execute the method for generating a physical examination conclusion as described in any one of the implementation modes of the first aspect.

[0013] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the method described in any one implementation of the first aspect.

[0014] According to a fifth aspect of the present disclosure, a computer program product is provided. When the computer program is executed by a processor, the method for generating a physical examination conclusion according to any one of the first aspects is implemented.

[0015] The present embodiment provides a method and device for generating a physical examination main examination conclusion, and a computer program product, wherein the method includes obtaining physical examination data sent by a terminal, and determining the initial conclusion structured data corresponding to the physical examination data based on a pre-trained large model; obtaining the specified auxiliary information input by the user at the terminal from the terminal; and using a rule engine to perform logical judgment on the initial conclusion structured data and the specified auxiliary information to output the main examination conclusion corresponding to the physical examination data. By combining the large model and rule engine technology, the accuracy and processing efficiency of the physical examination conclusion are improved, thereby overcoming the defect that the efficiency of manual main examination in the related technology needs to be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the specific embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 is a flow chart of a method for generating a physical examination conclusion according to an embodiment of the present invention; Figure 2 This is an application scenario diagram of the method for generating a physical examination main examination conclusion according to an embodiment of the present invention; Figure 3 is a schematic diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the scheme of the present disclosure, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present disclosure.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so as to describe the embodiments of the present disclosure described herein. 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 necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0021] According to an embodiment of the present disclosure, a method for generating a physical examination conclusion is provided, such as Figure 1 As shown, it includes the following steps 101 to 103: Step 101: Obtain the physical examination data sent by the terminal, and determine the initial conclusion structured data corresponding to the physical examination data based on the pre-trained large model.

[0022] In this step, the user can input the physical examination data on the terminal through a web page or APP. After receiving the physical examination data, the server calls the pre-trained large model for text prediction. After large-model processing, the initial conclusion structured data can be obtained.

[0023] Furthermore, the initial conclusion structured data includes target abnormality description, target standard words, target disease site, target size, target quantity, and target level corresponding to the physical examination data.

[0024] As an optional implementation method of this embodiment, when training the big model: obtain physical examination data training samples, and annotate the training samples to obtain department summary, examination findings, abnormal description, standard words, onset site, size, quantity, and grade; use the department summary and examination findings as input of the big model, and use the abnormal description, standard words, onset site, size, quantity, and grade as output of the big model to train the big model to obtain a pre-trained big model.

[0025] In this optional implementation, the physical examination data is collected and cleaned and preprocessed, and invalid, repeated or erroneous information can be removed by cleaning the collected data. After the data cleaning is completed, training samples are obtained, and then the training samples are labeled.

[0026] refer to Figure 2 The labeled data include department summary, examination findings, abnormal description, standard words, onset site, size, quantity, and grade data, among which department summary and examination findings are the input elements of the large model, and abnormal description, standard words, onset site, size, quantity, and grade are the output elements of the model.

[0027] Use the labeled training data set to perform supervised fine-tuning on the large model, including obtaining model input one by one from the labeled data pool, constructing the input parameters for this round of training according to the department summary and examination findings, and continuously iterating and optimizing the model parameters based on the similarity calculation between the model output and the labeled results, so as to improve the model's performance in the abnormality extraction task and enable it to accurately extract and identify abnormalities and structured information from physical examination data.

[0028] The trained big model is deployed in the server, and the main inspection system of the physical examination conclusion is provided with services through HTTP. The main inspection system of the physical examination conclusion extracts abnormal problems and the corresponding structured data from the physical examination data by calling the big model, and stores them in the database.

[0029] Step 102: Acquire, from the terminal, designated auxiliary information input by the user in the terminal.

[0030] As an optional implementation of this embodiment, obtaining the specified auxiliary information input by the user at the terminal from the terminal includes: obtaining the case information corresponding to the physical examination data; obtaining the auxiliary examination results corresponding to the physical examination data; obtaining the judgment information of whether to do the examination, and obtaining the information of all previous physical examinations. In this optional implementation, the case information includes basic information, specific case information, and questionnaire survey data; the auxiliary examination results include routine examination results, laboratory examination results, imaging examination results, and special examination results.

[0031] Exemplarily, basic information includes but is not limited to gender, age, and marital status; case information includes but is not limited to current medical history and past medical history; questionnaire data is in the form of an electronic questionnaire, including but not limited to drinking and smoking conditions, occupation and living environment, and sleep conditions.

[0032] Routine examination results, laboratory examination results, imaging examination results, and special examination results are custom classifications of auxiliary examination results, which serve as carriers of physical examination result information. Routine examination results: Examination results diagnosed by a doctor after examination, usually descriptive text, such as lung breath sound examination in internal medicine, spinal examination in surgery, etc. Laboratory examination results: Examination results obtained by instruments and equipment, usually specific values, such as red blood cell count, mean corpuscular volume, etc. Imaging examination results: Examination results obtained by doctors after the information collected by instruments and equipment is processed, such as CT, bone density, electrocardiogram, etc. The judgment information on whether to do an examination is to judge whether a specific examination item has been done during the physical examination, such as a routine blood test. Information on previous physical examinations is whether the person being examined has had a physical examination before, which can be combined with whether the examination has been done to indicate whether the examination item has been done before.

[0033] Step 103: Use a rule engine to perform logical judgment on the initial conclusion structured data and designated auxiliary information to output the main examination conclusion corresponding to the physical examination data, wherein the input information, logical judgment conditions, and output information are configured in a visual configuration manner to form the rules of the rule engine; the logical judgment conditions are defined as judging whether the value of the input information satisfies any condition, whether it satisfies some conditions, or whether it satisfies all conditions; the output information is defined as diagnostic disease information, suspected disease information, or abnormal problem information; when configuring the rule of the rule engine, each input information is combined in a visual configuration manner, the combined input information is combined with different logical judgment conditions in a visual configuration manner to obtain a judgment combination, and the judgment combination is combined with different output information in a visual configuration manner to obtain the rule of the rule engine.

[0034] In the above steps, the auxiliary information specified by the user is obtained from the terminal, and the rule engine is used to perform conditional judgment based on the auxiliary information and the information determined by the large model, and then the final main inspection conclusion is output.

[0035] Specifically, the rules of the rule engine can be abstracted into input, logical judgment conditions, and output. The rules specify different outputs based on different inputs and different logical judgment conditions, where both the input and logical judgment conditions can be configured through visual configuration. The input after visual configuration is obtained by specifying auxiliary information and initialization structure data, which can be any N items of the specified auxiliary information, where N is a natural number, the maximum is the number of information items in the specified auxiliary information, the combination of any N items of the specified auxiliary information and any M items of the initialization structure data, and any M items of the initialization structure data, where M is a natural number, the maximum is the number of information items in the initialization structure data.

[0036] Furthermore, the logical judgment condition indicates that when any one of the different inputs is met, part of the different inputs is met, or all of the different inputs are met, the corresponding output is different diagnosed diseases, different suspected diseases, and / or different abnormal problems.

[0037] Furthermore, input, output, and logical judgment conditions are abstracted based on medical standards and specifications. By abstracting the input and logical judgment conditions, accurate and rich output is achieved. Therefore, based on the abstraction, the way to achieve visual configuration can be to provide a graphical interface for the terminal, and the user can directly drag the corresponding input elements and logical judgment conditions to achieve different outputs.

[0038] For example, taking the laboratory test results as the input of the auxiliary examination results, the input of the laboratory test results includes 17 elevated pepsin test results, pepsinogen I includes decreased, pepsinogen I includes increased, pepsinogen II results include increased, pepsin II results include decreased, pepsinogen ratio results include decreased, and PGI / PGII results include decreased; then the preset logical judgment condition here can be the "satisfy any one" of the visual configuration, and the output can be the diagnosis of the disease as "abnormal gastric serological examination".

[0039] From the above, we can see that the rules of the rule engine are not fixed. Both the input and the logical judgment conditions can be flexibly adjusted and configured through visual configuration, so that they can flexibly adapt to changes in standards and specifications.

[0040] After configuring the rules, the rule engine can be used to perform logical judgment on the input initial conclusion structured data and specified auxiliary information to output the main inspection conclusion.

[0041] As an optional implementation method of this embodiment, using a rule engine to perform logical judgment on the initial conclusion structured data and designated auxiliary information includes: taking the initial conclusion structured data and designated auxiliary information as input to the rule engine; determining corresponding logical judgment conditions based on the input, and outputting the main examination conclusion corresponding to the physical examination data according to the judgment logic of the logical judgment conditions.

[0042] In this optional implementation, since different inputs, different logical judgment conditions, and corresponding different outputs are specified in the rules, after the input is obtained, different judgment results can be output based on the logical judgment conditions in different rules.

[0043] As an optional implementation manner of this embodiment, the method further includes: obtaining feedback suggestions for the main inspection conclusion; and optimizing the rules of the rule engine based on the feedback suggestions.

[0044] In this optional implementation, a feedback mechanism is designed to output the physical examination conclusion and the main examination report to the doctor so that the doctor can make further diagnosis and treatment suggestions based on the physical examination conclusion and optimize the rule engine.

[0045] When optimizing the rule engine, based on feedback suggestions, existing rules can be modified, deleted, or added. For example, one or more of the input, logical judgment conditions, or output of the rule can be modified, deleted, or added. After the adjustment is completed, the same input may correspond to different main inspection conclusions.

[0046] This embodiment improves the accuracy and processing efficiency of physical examination conclusions by combining large models and rule engine technology. Specifically, the examination description in the physical examination report is input into a large pre-trained model, and the model generates possible abnormal structured information based on this data. Then, this structured information is input into the rule engine, analyzed and judged according to predefined rules, and finally the physical examination conclusion is generated. On the one hand, this method can reduce the workload of doctors and improve work efficiency; on the other hand, it can also realize intelligent analysis and mining of physical examination data, and improve the accuracy and reliability of physical examination conclusions.

[0047] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0048] According to an embodiment of the present disclosure, there is also provided a device for generating a main conclusion of a physical examination, comprising a large model calling unit, configured to obtain physical examination data sent by a terminal, and determine initial conclusion structured data corresponding to the physical examination data based on a pre-trained large model; an auxiliary information obtaining unit, configured to obtain designated auxiliary information input by a user at the terminal from the terminal; an output unit, configured to use a rule engine to perform logical judgment on the initial conclusion structured data and the designated auxiliary information to output a main conclusion corresponding to the physical examination data; wherein the input information, logical judgment conditions, and output information are configured in a visual configuration manner to form a rule of the rule engine; the logical judgment conditions are defined as judging whether the value of the input information satisfies any condition, whether it satisfies some conditions, or whether it satisfies all conditions; the output information is defined as diagnostic disease information, suspected disease information, or abnormal problem information; when configuring the rule of the rule engine, each input information is combined in a visual configuration manner, the combined input information is combined with different logical judgment conditions in a visual configuration manner to obtain a judgment combination, and the judgment combination is combined with different output information in a visual configuration manner to obtain the rule of the rule engine.

[0049] As an optional implementation method of this embodiment, using a rule engine to perform logical judgment on the initial conclusion structured data and designated auxiliary information includes taking the initial conclusion structured data and designated auxiliary information as inputs of the rule engine; determining corresponding logical judgment conditions based on the inputs, and outputting the main examination conclusion corresponding to the physical examination data according to the judgment logic of the logical judgment conditions.

[0050] As an optional implementation of this embodiment, the method also includes: obtaining feedback suggestions for the main inspection conclusion; optimizing the rules of the rule engine based on the feedback suggestions, including: optimizing the input information, logical judgment conditions, and / or output information of the rules.

[0051] As an optional implementation method of this embodiment, when training the big model: obtain physical examination data training samples, and annotate the training samples to obtain department summary, examination findings, abnormal description, standard words, onset site, size, quantity, and grade; use the department summary and examination findings as input of the big model, and use the abnormal description, standard words, onset site, size, quantity, and grade as output of the big model to train the big model to obtain a pre-trained big model.

[0052] As an optional implementation method of this embodiment, the initial conclusion structured data corresponding to the physical examination data is determined based on the pre-trained big model, including: determining the target abnormality description, target standard word, target onset site, target size, target quantity, and target level corresponding to the physical examination data based on the pre-trained big model.

[0053] As an optional implementation method of this embodiment, obtaining specified auxiliary information input by the user at the terminal from the terminal includes: obtaining case information corresponding to the physical examination data, wherein the case information includes basic information, specific case information, and questionnaire survey data; obtaining auxiliary examination results corresponding to the physical examination data; obtaining judgment information on whether to perform an examination, and obtaining previous physical examination information.

[0054] According to an embodiment of the present invention, the present invention further provides a computer program product, which can implement the method described in any of the above embodiments when executed by a processor.

[0055] Figure 3 A schematic block diagram of an example electronic device 300 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices.

[0056] like Figure 3 As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0057] A number of components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0058] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as the object matching method. For example, in some embodiments, the object matching method may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the method described above may be performed.

[0059] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0060] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0061] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Claims

1. A method for generating a physical examination conclusion, characterized in that: include: Obtain the physical examination data sent by the terminal, and determine the initial conclusion structured data corresponding to the physical examination data based on the pre-trained large model; Acquire, from the terminal, designated auxiliary information input by the user in the terminal; Using a rule engine to perform logical judgment on the initial conclusion structured data and the specified auxiliary information to output a main examination conclusion corresponding to the physical examination data; The rules of the rule engine are composed of input information, logical judgment conditions, and output information configured in a visual configuration manner; the logical judgment condition is defined as judging whether the value of the input information satisfies any condition, whether it satisfies some conditions, or whether it satisfies all conditions; the output information is defined as diagnostic disease information, suspected disease information, or abnormal problem information; When configuring the rule engine rules, each input information is combined through a visual configuration method, the combined input information is combined with different logical judgment conditions through a visual configuration method to obtain a judgment combination, and the judgment combination is combined with different output information through a visual configuration method to obtain the rule of the rule engine.

2. The method for generating a physical examination conclusion according to claim 1, characterized in that: Using the rule engine to perform logical judgment on the initial conclusion structured data and the specified auxiliary information includes: Using the initial conclusion structured data and the specified auxiliary information as input to the rule engine; A corresponding logical judgment condition is determined based on the input, and a main examination conclusion corresponding to the physical examination data is output according to the judgment logic of the logical judgment condition.

3. The method for generating a physical examination conclusion according to claim 2, characterized in that: The method further comprises: Obtain feedback and suggestions on the main inspection conclusions; Optimizing the rules of the rule engine based on the feedback suggestion includes: optimizing the input information, logical judgment conditions, and / or output information of the rule.

4. The method for generating a physical examination conclusion according to claim 1, characterized in that: When training the large model: Obtaining physical examination data training samples, and annotating the training samples to obtain department summary, examination findings, abnormal description, standard words, onset site, size, quantity, and grade; The department summary and examination findings are used as inputs of the big model, and the abnormal description, standard words, onset site, size, quantity, and level are used as outputs of the big model to train the big model to obtain a pre-trained big model.

5. The method for generating a physical examination conclusion according to claim 3, characterized in that: The initial conclusion structured data corresponding to the physical examination data determined based on the pre-trained large model includes: The target abnormality description, target standard word, target disease site, target size, target quantity, and target level corresponding to the physical examination data are determined based on the pre-trained large model.

6. The method for generating a physical examination conclusion according to claim 2, characterized in that: Obtaining the specified auxiliary information input by the user at the terminal from the terminal includes: Obtaining case information corresponding to the physical examination data; Obtaining auxiliary examination results corresponding to the physical examination data; Obtain information on whether to undergo an examination and obtain information on previous physical examinations.

7. A physical examination conclusion generating device, characterized in that: include: The large model calling unit is configured to obtain the physical examination data sent by the terminal, and determine the initial conclusion structured data corresponding to the physical examination data based on the pre-trained large model; an auxiliary information acquisition unit, configured to acquire, from the terminal, designated auxiliary information input by a user in the terminal; An output unit is configured to use a rule engine to perform logical judgment on the initial conclusion structured data and the specified auxiliary information to output a main examination conclusion corresponding to the physical examination data; The rules of the rule engine are composed of input information, logical judgment conditions, and output information configured in a visual configuration manner; the logical judgment condition is defined as judging whether the value of the input information satisfies any condition, whether it satisfies some conditions, or whether it satisfies all conditions; the output information is defined as diagnostic disease information, suspected disease information, or abnormal problem information; When configuring the rule engine rules, each input information is combined through a visual configuration method, the combined input information is combined with different logical judgment conditions through a visual configuration method to obtain a judgment combination, and the judgment combination is combined with different output information through a visual configuration method to obtain the rule of the rule engine.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method for generating a physical examination conclusion according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: at least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the method for generating the main physical examination conclusion as described in any one of claims 1-6.

10. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the method for generating a physical examination conclusion according to any one of claims 1 to 6.

Images