Operation consistency detection method, device, equipment, medium and program product

Abstract

The invention provides an operation consistency detection method and device, equipment, a medium and a program product. The operation consistency detection method comprises the steps that a first key element corresponding to a first operation name in operation process description is extracted; extracting a second key element corresponding to a second operation name in the target data; comparing the first key element with the second key element to obtain a comparison result; and based on the comparison result, determining a consistency detection result of the second operation name and the operation process description in the target data. The detection accuracy of detecting whether the operation name is consistent with the actual operation or not can be improved.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a surgical consistency detection method, device, equipment, medium and program product. Background Art

[0002] In recent years, with the advancement and deepening of the reform of medical insurance payment methods, payment by Diagnosis-Related Groups (DRG) and Diagnosis-Intervention Packet (DIP) have been piloted and verified in many places. During the implementation process, the accuracy of the operation name filled in on the medical record homepage and the settlement list directly affects whether a medical record can be reasonably included in the group.

[0003] From the hospital's perspective, if the name of the operation filled in on the medical record's front page is inconsistent with the actual hospitalization process due to insufficient knowledge of the coder, resulting in enrollment errors, the actual medical insurance payment will further change, which may harm the interests of the hospital; from the medical insurance perspective, if the hospital has an operation that is over-coded, under-coded, and written more in order to obtain more medical insurance payments, it will cause irrational use of medical insurance funds.

[0004] At present, it is particularly important to improve the accuracy of detecting whether the name of the surgery is consistent with the actual surgery. Summary of the invention

[0005] The present application provides a method, device, equipment, medium and program product for detecting the consistency of surgery, which are used to improve the accuracy of detecting whether the name of the surgery is consistent with the actual surgery.

[0006] According to a first aspect of an embodiment of the present application, a method for detecting surgical consistency is provided, comprising:

[0007] Extracting the first key element corresponding to the first surgery name in the surgical procedure description;

[0008] Extracting a second key element corresponding to a second surgery name in the target data;

[0009] Comparing the first key element and the second key element to obtain a comparison result;

[0010] Based on the comparison result, a consistency detection result between the second operation name in the target data and the operation procedure description is determined.

[0011] Optionally, extracting the first key element corresponding to the first surgery name in the surgical procedure description includes:

[0012] Based on the description of the surgical procedure, a first prompt word is generated;

[0013] Inputting the first prompt word into the large model to obtain a first key element corresponding to the first surgery name in the surgical procedure description;

[0014] The first prompt word is used to instruct the large model to extract the first key element corresponding to the first operation name in the description of the surgical procedure.

[0015] Optionally, extracting the second key element corresponding to the second surgery name in the target data includes:

[0016] generating a second prompt word based on the second surgery name in the target data;

[0017] Inputting the second prompt word into the large model to obtain a second key element corresponding to the second surgery name in the target data;

[0018] The second prompt word is used to indicate that the large model extracts a second key element corresponding to the second surgery name in the target data.

[0019] Optionally, the first surgery name corresponds to a plurality of first key elements, the second surgery name corresponds to a plurality of second key elements, and one first key element corresponds to one second key element;

[0020] The comparing the first key element and the second key element to obtain a comparison result includes:

[0021] Comparing any one of the first key elements with a second key element corresponding to the first key element, and obtaining a single comparison result corresponding to the first key element;

[0022] A comparison result is obtained based on the individual comparison results corresponding to each first key element.

[0023] Optionally, the comparing any one of the first key elements with a second key element corresponding to the any one of the first key elements to obtain a single comparison result corresponding to the any one of the first key elements includes:

[0024] Generate a third prompt word based on any one of the first key elements and a second key element corresponding to the any one of the first key elements;

[0025] Inputting the third prompt word into the large model to obtain a single comparison result corresponding to any one of the first key elements;

[0026] The third prompt word is used to instruct the large model to compare any one of the first key elements with the second key element corresponding to the any one of the first key elements, and obtain a single comparison result corresponding to the any one of the first key elements.

[0027] Optionally, the first key element includes a first anatomical site, a first resection range, a first surgical procedure and a first approach; the second key element includes a second anatomical site, a second resection range, a second surgical procedure and a second approach;

[0028] The single comparison result corresponding to the first anatomical part includes whether the first anatomical part and the second anatomical part are consistent and the corresponding reason, or whether the first anatomical part and the second anatomical part have an inclusion relationship and the corresponding reason;

[0029] The single comparison result corresponding to the first resection range includes whether the first resection range is consistent with the second resection range and the corresponding reasons;

[0030] The single comparison result corresponding to the first surgical procedure includes whether the first surgical procedure is consistent with the second surgical procedure and the corresponding reasons;

[0031] The single comparison result corresponding to the first approach includes whether the first approach is consistent with the second approach and the corresponding reason.

[0032] Optionally, determining the consistency detection result between the second surgery name in the target data and the surgical procedure description based on the comparison result includes:

[0033] In the case where the comparison result satisfies a preset condition, determining that a consistency detection result of the second operation name in the target data and the surgical procedure description is that the second operation name in the target data and the surgical procedure description are consistent;

[0034] In the case where the comparison result does not satisfy the preset condition, determining that the consistency detection result of the second operation name in the target data and the surgical procedure description is that the second operation name in the target data and the surgical procedure description are inconsistent;

[0035] Among them, the preset conditions include that the first anatomical part and the second anatomical part are consistent or have an inclusion relationship, and the first resection range and the second resection range are consistent, and the first surgical procedure and the second surgical procedure are consistent, and the first approach and the second approach are consistent.

[0036] Optionally, the target data includes at least one of a medical record cover page and a settlement list.

[0037] According to a second aspect of an embodiment of the present application, a surgical consistency detection device is provided, comprising:

[0038] A first extraction unit, used to extract a first key element corresponding to a first surgery name in the surgical procedure description;

[0039] A second extraction unit is used to extract a second key element corresponding to a second surgery name in the target data;

[0040] A comparison unit, used for comparing the first key element and the second key element to obtain a comparison result;

[0041] A detection unit is used to determine a consistency detection result between the second operation name in the target data and the description of the operation process based on the comparison result.

[0042] According to a third aspect of an embodiment of the present application, there is provided an electronic device, including a memory and a processor;

[0043] The memory is connected to the processor and is used to store programs;

[0044] The processor is used to implement the surgical consistency detection method as described in the first aspect by running the program in the memory.

[0045] According to a fourth aspect of an embodiment of the present application, a storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the surgical consistency detection method as described in the first aspect is implemented.

[0046] According to a fifth aspect of an embodiment of the present application, a computer program product is provided, comprising computer program instructions, which, when executed by a processor, enable the processor to execute the surgical consistency detection method as described in the first aspect.

[0047] In the present application, the first key element corresponding to the first operation name in the surgical procedure description is extracted, the second key element corresponding to the second operation name in the target data is extracted, the first key element and the second key element are compared to obtain a comparison result, and based on the comparison result, the consistency detection result of the second operation name in the target data and the surgical procedure description is determined. The first key element and the second key element contain more surgical detail information. By comparing the first key element and the second key element, the consistency detection result of the second operation name in the target data and the surgical procedure description is determined. Compared with directly comparing the first operation name and the second operation name, the detection accuracy of whether the second operation name in the target data and the surgical procedure description are consistent can be improved. Since the surgical procedure description can reflect the surgical operation of the patient during the actual hospitalization process, the detection accuracy of whether the second operation name in the target data is consistent with the actual operation can be further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0049] Figure 1 A schematic diagram of a flow chart of a surgical consistency detection method provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of a process of step 101 provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of a process of step 102 provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of a process of step 103 provided in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of a process of step 401 provided in an embodiment of the present application;

[0054] Figure 6 This is a schematic diagram of the structure of a surgical consistency detection device provided in an embodiment of the present application;

[0055] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] 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 only 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.

[0057] Exemplary Implementation Environment

[0058] The surgical consistency detection method according to the embodiment of the present application can be executed by an electronic device such as a terminal device or a server. The terminal device can be a user device, a mobile device, a computing device, a wearable device, etc. The server can be an independent physical server, a server cluster composed of multiple physical servers, or a cloud server capable of cloud computing. The method can be implemented by a processor calling a computer-readable program instruction stored in a memory.

[0059] Exemplary Methods

[0060] See also Figure 1 In an exemplary embodiment, a method for detecting surgical consistency is provided. Figure 1 As shown, the process of the surgical consistency detection method mainly includes:

[0061] Step 101: extracting a first key element corresponding to a first operation name in a description of an operation procedure.

[0062] In an exemplary embodiment, the surgical procedure description is extracted from the surgical record, and the surgical procedure description can reflect the actual surgical operation of the patient during hospitalization.

[0063] In an exemplary embodiment, an exemplary surgical procedure is described as follows:

[0064] After successful general anesthesia, the shoulders were raised and the head was tilted back to fully expose the neck. The surgical field was disinfected with 0.5% iodine. A transverse arc incision was made through the neck, about 6 cm long. The skin was cut, the surgical scars, subcutaneous tissue, and platysma muscle of the neck were removed in sequence, and a free flap was made under the platysma muscle, from the thyroid cartilage to the sternal notch. The white line of the neck was cut to reach the surgical capsule of the thyroid gland. The capsule was opened and the anterior neck muscles were pulled apart to fully expose the thyroid gland lobe. Several lumps were palpable in the left lobe of the thyroid gland, the largest of which was about 1.0*0.5cm, with a tough texture, smooth surface, and clear boundaries. It was decided to perform radical resection of left thyroid cancer. The left lobe of the thyroid gland was pulled inward to free the outer edge, the middle vein was cut and ligated with an ultrasonic knife, the thyroid gland was pulled down, the upper pole blood vessels were cut and ligated, the thyroid gland was pulled upward, the lower pole blood vessels were cut and ligated, and the thyroid gland was pulled inward to expose the recurrent laryngeal nerve and parathyroid gland, and the left lobe of the thyroid gland and the gland were completely removed. Careful hemostasis, suture and ligation were performed one by one, and it was reliable. After further examination of the surgical field, the recurrent laryngeal nerve was well exposed and no active bleeding was confirmed, and the incision was sutured layer by layer.

[0065] In an exemplary embodiment, the surgical procedure description may include one first surgical procedure name or at least two first surgical procedure names, depending on the actual surgical situation, and the present application does not limit this. In the case where the surgical procedure description includes one first surgical procedure name, step 101 includes: directly extracting the first key element corresponding to the first surgical procedure name in the surgical procedure description. In the case where the surgical procedure description includes at least two first surgical procedure names, step 101 includes: extracting the first key element corresponding to each first surgical procedure name in the surgical procedure description.

[0066] In some embodiments, Figure 2 As shown, step 101 includes:

[0067] Step 201: Generate a first prompt word based on the description of the surgical procedure.

[0068] In an exemplary embodiment, the first prompt word template corresponding to the first prompt word is "Surgical procedure: {input1}\n{prompt1}", where "\n" represents a line break, "{input1}" is used to fill in the surgical procedure description, and "{prompt1}" is used to fill in the question instruction. The question instruction can be "What surgeries are included in the above surgical procedure? Please list the names of the surgeries and explain their anatomical sites, resection ranges, surgical procedures, and approaches respectively? \nPlease output {Surgical name: {\n"anatomical site": anatomical site, \n"resection range": resection range, \n"procedure": procedure, \n"approach": approach}} in the following format. The surgical procedure refers to the method of surgery, such as the surgical procedure of adrenal autotransplantation is transplantation, and the surgical procedure of frontal muscle suture ptosis repair is repair; the approach refers to the way to enter the body lesion, such as the approach of laparoscopic anterior rectal resection with colostomy is laparoscopy." The question instructions include the content and format that the big model wants to output, as well as explanations and examples of some difficult-to-understand concepts, so that the big model can better understand the instructions and give accurate answers.

[0069] Step 202: input the first prompt word into the large model to obtain the first key element corresponding to the first operation name in the description of the surgical procedure.

[0070] The first prompt word is used to instruct the large model to extract the first key element corresponding to the first operation name in the description of the surgical procedure.

[0071] In an exemplary embodiment, an exemplary first prompt word is as follows:

[0072] Operation process: After successful general anesthesia, the shoulders are raised and the head is tilted back to fully expose the neck. The surgical field is disinfected with 0.5% iodine. A transverse arc incision is made through the neck, about 6 cm long. The skin is cut, the surgical scar, subcutaneous tissue, and platysma muscle of the neck are removed in sequence. A free flap is made under the platysma muscle, from the thyroid cartilage to the sternal notch, and the white line of the neck is cut to reach the surgical capsule of the thyroid gland. The capsule is opened and the anterior neck muscles are pulled apart to both sides to fully expose the thyroid gland lobe. Several lumps can be palpated in the left lobe of the thyroid gland. The largest one is about 1.0*0.5cm, with a tough texture, smooth surface, and clear boundaries. It is decided to perform radical resection of left thyroid cancer. The left lobe thyroid gland is pulled inward to free the outer edge, the middle vein is cut and ligated with an ultrasonic knife, the thyroid gland is pulled down, the upper pole blood vessels are cut and ligated, the thyroid gland is pulled upward, the lower pole blood vessels are cut and ligated, and the thyroid gland is pulled inward to expose the recurrent laryngeal nerve and parathyroid gland, and the left lobe thyroid gland mass and gland are completely removed. Careful hemostasis, suture and ligation one by one, reliable. After further examination of the surgical field, the recurrent laryngeal nerve was well exposed and there was no active bleeding. The incision was sutured layer by layer. What surgeries are included in the above surgical procedure? Please list the names of the surgeries and explain their anatomical sites, resection range, surgical procedures, and approaches.

[0073] Please output {operation name:{\n"anatomical site":anatomical site,\n"excision range":excision range,\n"procedure":procedure,\n"approach":approach}} in the following format. The procedure refers to the surgical method, such as the procedure of adrenal autotransplantation is transplantation, and the procedure of frontalis suture ptosis repair is repair; the approach refers to the way to enter the body lesion, such as the approach of laparoscopic anterior rectal resection with colostomy is laparoscopy.

[0074] This exemplary first prompt word is input into the large model, and the output of the large model is as follows:

[0075] According to the surgical process you provided, this is a radical resection of left thyroid cancer. The specific information is as follows:

[0076] {

[0077] "Radical thyroidectomy":{

[0078] "Anatomical part":"Neck",

[0079] "Resection range":"Left lobe of thyroid gland",

[0080] "Operative procedure":"resection",

[0081] "Approach": "Neck incision"

[0082] }

[0083] }

[0084] In the output content of the above large model, the name of the first operation is radical resection of left thyroid cancer. The first key elements corresponding to the first operation name include the first anatomical site, the first resection range, the first surgical procedure and the first approach. The first anatomical site is the neck, the first resection range is the left lobe of the thyroid gland, the first surgical procedure is resection, and the first approach is the neck incision.

[0085] Based on the surgical procedure description, a first prompt word is generated, and the first prompt word is input into the big model to obtain the first key element corresponding to the first surgery name in the surgical procedure description. The first key element corresponding to the first surgery name in the surgical procedure description is extracted through the big model, which makes full use of the language comprehension ability of the big model, is not bound by the construction of prior knowledge, improves generalization, can accurately extract the first key element corresponding to the first surgery name in the surgical procedure description, and can improve the efficiency of extracting the first key element corresponding to the first surgery name in the surgical procedure description.

[0086] In other embodiments, step 101 includes: extracting a first key element corresponding to a first operation name in the surgical procedure description through keyword matching.

[0087] Step 102: extracting a second key element corresponding to a second operation name in the target data.

[0088] In some embodiments, the target data includes at least one of the medical record homepage and the settlement list. The correctness of the operation name filled in the medical record homepage and the settlement list directly affects whether a medical record can be reasonably included in the group, thereby affecting the medical insurance payment. Therefore, according to needs, the target data can be set as the medical record homepage, and then detect whether the second operation name in the medical record homepage is consistent with the description of the surgical process; or, the target data can be set as the settlement list, and then detect whether the second operation name in the settlement list is consistent with the description of the surgical process; or, the target data can be set as the medical record homepage and the settlement list, and then detect whether the second operation name in the medical record homepage and the settlement list is consistent with the description of the surgical process.

[0089] In an exemplary embodiment, the name of the second operation in an exemplary target data is as follows: laparoscopic total thyroidectomy.

[0090] In an exemplary embodiment, the target data may include one second surgical name or at least two second surgical names, depending on the actual situation, and the present application does not limit this. In the case where the target data includes one second surgical name, step 102 includes: directly extracting the second key element corresponding to the second surgical name in the target data. In the case where the target data includes at least two second surgical names, step 102 includes: extracting the second key element corresponding to each second surgical name in the target data.

[0091] In some embodiments, Figure 3 As shown, step 102 includes:

[0092] Step 301, generating a second prompt word based on the second surgery name in the target data.

[0093] In an exemplary embodiment, the second prompt word template corresponding to the second prompt word is "What are the anatomical site, resection range, surgical procedure, and approach of {input2}? \nPlease output {operation name: {\n"anatomical site": anatomical site, \n"resection range": resection range, \n"procedure": procedure, \n"approach": approach}} in the following format. The surgical procedure refers to the method of surgery, such as the procedure of adrenal autotransplantation is transplantation, and the procedure of frontal muscle suture ptosis repair is repair; the approach refers to the way to enter the body lesion, such as the approach of laparoscopic anterior rectal resection with colostomy is laparoscopic", where "\n" represents a line break, and "{input2}" is used to fill in the second surgical name in the target data.

[0094] Step 302, input the second prompt word into the large model to obtain the second key element corresponding to the second surgery name in the target data.

[0095] The second prompt word is used to instruct the large model to extract the second key element corresponding to the second surgery name in the target data.

[0096] In an exemplary embodiment, an exemplary second prompt word is as follows:

[0097] What are the anatomical location, resection range, surgical procedure and approach of "laparoscopic total thyroidectomy"?

[0098] Please output {operation name:{\n"anatomical site":anatomical site,\n"excision range":excision range,\n"procedure":procedure,\n"approach":approach}} in the following format. The procedure refers to the surgical method, such as the procedure of adrenal autotransplantation is transplantation, and the procedure of frontalis suture ptosis repair is repair; the approach refers to the way to enter the body lesion, such as the approach of laparoscopic anterior rectal resection with colostomy is laparoscopy.

[0099] This exemplary second prompt word is input into the large model, and the output of the large model is as follows:

[0100] The surgical information of "Laparoscopic Total Thyroidectomy" is as follows:

[0101] {

[0102] "Laparoscopic total thyroidectomy":{

[0103] "Anatomy":"The neck, especially one side of the thyroid gland",

[0104] "Extent of resection":"The entire thyroid gland",

[0105] "Operative procedure":"resection",

[0106] "Approach":"Laparoscopic"

[0107] }

[0108] }

[0109] In the output content of the above large model, the second surgical name is laparoscopic total thyroidectomy. The second key elements corresponding to the second surgical name include the second anatomical site, the second resection range, the second surgical procedure and the second approach. The second anatomical site is the neck, especially one side of the thyroid gland. The second resection range is the entire thyroid gland. The second surgical procedure is resection, and the second approach is laparoscope.

[0110] Based on the second surgical name in the target data, a second prompt word is generated, and the second prompt word is input into the big model to obtain the second key element corresponding to the second surgical name in the target data. The second key element corresponding to the second surgical name in the target data is extracted through the big model, and the language comprehension ability of the big model is fully utilized. It is not restricted by the construction of prior knowledge, and the generalization is improved. The second key element corresponding to the second surgical name in the target data can be accurately extracted, and the efficiency of extracting the second key element corresponding to the second surgical name in the target data can be improved.

[0111] In other embodiments, step 102 includes: extracting a second key element corresponding to the second surgery name in the target data through keyword matching.

[0112] Step 103: compare the first key element and the second key element to obtain a comparison result.

[0113] In some embodiments, the first operation name corresponds to multiple first key elements, the second operation name corresponds to multiple second key elements, and one first key element corresponds to one second key element.

[0114] In some embodiments, Figure 4 As shown, step 103 includes:

[0115] Step 401 : compare any first key element with any second key element corresponding to the first key element, and obtain a single comparison result corresponding to any first key element.

[0116] In some embodiments, Figure 5 As shown, step 401 includes:

[0117] Step 501: Generate a third prompt word based on any first key element and any second key element corresponding to the first key element.

[0118] In an exemplary embodiment, the third prompt word template corresponding to the third prompt word is "Text 1: {content1}. Text 2: {content2}. \nAre the {point} descriptions of the above two surgical operations consistent? Please answer yes or no, and explain the reason", where "{content1}" is used to fill in the first key element corresponding to the first surgical name in the surgical process description, "{content2}" is used to fill in the second key element corresponding to the second surgical name in the target data, and "{point}" is used to fill in the element point to be reviewed. In particular, the anatomical parts are allowed to have a superior and subordinate inclusion relationship. Since the part descriptions are rough and detailed, the review scale for this part is appropriately looser. Therefore, the third prompt word template for reviewing the anatomical parts is "Text 1: {content1}. Text 2: {content2}. \nAre the anatomical part descriptions of the above two surgical operations consistent or do they have an inclusion relationship? Please answer yes or no, and explain the reason".

[0119] Step 502: input the third prompt word into the large model to obtain a single comparison result corresponding to any first key element.

[0120] The third prompt word is used to instruct the large model to compare any first key element with any second key element corresponding to the first key element, and obtain a single comparison result corresponding to any first key element.

[0121] In an exemplary embodiment, when any one of the first key elements is a first anatomical part, and any one of the second key elements corresponding to the first key element is a second anatomical part, an exemplary third prompt word is as follows:

[0122] Text 1: Neck. Text 2: Neck, especially the side of the thyroid gland.

[0123] Are the anatomical parts described in the above two surgical procedures consistent or are they included in each other? Please answer yes or no and explain your reasons.

[0124] This exemplary third prompt word is input into the large model, and the output of the large model is as follows:

[0125] Yes, there is an inclusion relationship between the descriptions of the two anatomical parts.

[0126] "Neck" is a broad area that includes many structures, such as skin, muscles, blood vessels, nerves, thyroid gland, larynx, trachea, etc. "Neck, especially one side of the thyroid gland" is a more specific description that refers to a specific area in the neck, namely one side of the thyroid gland. Therefore, although the two are not completely consistent, "neck, especially one side of the thyroid gland" is a subset of "neck" and has an inclusion relationship.

[0127] In an exemplary embodiment, when any one of the first key elements is a first resection range and any one of the second key elements corresponding to the first key element is a second resection range, an exemplary third prompt word is as follows:

[0128] Text 1: Unilateral thyroid gland. Text 2: The entire thyroid gland.

[0129] Are the excision ranges described in the above two surgical procedures consistent? Please answer yes or no and explain your reasons.

[0130] This exemplary third prompt word is input into the large model, and the output of the large model is as follows:

[0131] No, the two descriptions of resection range do not have the same meaning.

[0132] "Unilateral thyroid" refers to one side of the thyroid gland, which can be the left or right side, and the specific side needs to be determined based on the context or other information. On the other hand, "entire thyroid gland" clearly indicates that the entire thyroid gland is removed, including the left and right sides. Therefore, the meanings of these two descriptions are not consistent.

[0133] In an exemplary embodiment, when any first key element is a first technique, and any second key element corresponding to the first key element is a second technique, an exemplary third prompt word is as follows:

[0134] Text 1: Resection. Text 2: Resection.

[0135] Are the surgical procedures described in the above two cases consistent? Please answer yes or no and explain why.

[0136] This exemplary third prompt word is input into the large model, and the output of the large model is as follows:

[0137] Yes, the description of the two surgical procedures is consistent.

[0138] "Resection" is a surgical procedure that involves the complete or partial removal of diseased tissue or organs. Both Text 1 and Text 2 describe "resection", so their descriptions of the procedure are consistent.

[0139] In an exemplary embodiment, when any one of the first key elements is a first approach and any one of the second key elements corresponding to the first key element is a second approach, an exemplary third prompt word is as follows:

[0140] Text 1: Neck incision. Text 2: Laparoscopy.

[0141] Are the approaches described for the two surgical procedures consistent? Please answer yes or no and explain why.

[0142] This exemplary third prompt word is input into the large model, and the output of the large model is as follows:

[0143] No, the approaches described for the two surgical procedures are inconsistent.

[0144] "Neck incision" describes surgery performed through an incision in the neck, which is a traditional open surgical method. "Laparoscopic" is a minimally invasive surgical technique that inserts a laparoscope into a natural cavity in the body or a small hole in the skin, without the need for a large incision at the surgical site.

[0145] Therefore, the surgical approaches described by "neck incision" and "laparoscopy" are inconsistent.

[0146] Based on any first key element and any second key element corresponding to the first key element, a third prompt word is generated, and the third prompt word is input into the big model to obtain a single comparison result corresponding to any first key element. By comparing any first key element with any second key element corresponding to the first key element through the big model, a single comparison result corresponding to any first key element is obtained. The language comprehension ability of the big model is fully utilized, and it is not restricted by the construction of prior knowledge, thereby improving generalization, and being able to accurately obtain a single comparison result corresponding to any first key element.

[0147] In other embodiments, step 401 includes: determining the semantic similarity between any first key element and any second key element corresponding to the first key element; and obtaining a single comparison result corresponding to any first key element based on the semantic similarity.

[0148] In some embodiments, the first key element includes a first anatomical site, a first resection range, a first surgical procedure, and a first approach. The second key element includes a second anatomical site, a second resection range, a second surgical procedure, and a second approach.

[0149] Among them, the anatomical site refers to the body area or organ involved in the operation. The resection range refers to the range of tissues or organs that need to be removed during the operation. The surgical procedure refers to the way of surgery. The approach refers to the way to enter the body lesion.

[0150] In some embodiments, the single comparison result corresponding to the first anatomical part includes whether the first anatomical part and the second anatomical part are consistent and the corresponding reason, or whether the first anatomical part and the second anatomical part have an inclusion relationship and the corresponding reason;

[0151] The single comparison result corresponding to the first resection range includes whether the first resection range and the second resection range are consistent and the corresponding reasons;

[0152] The single comparison result corresponding to the first surgical procedure includes whether the first surgical procedure and the second surgical procedure are consistent and the reasons for the correspondence;

[0153] The single comparison result corresponding to the first approach includes whether the first approach and the second approach are consistent and the reasons for the correspondence.

[0154] In an exemplary embodiment, whether the first anatomical part and the second anatomical part are consistent, whether the first resection range and the second resection range are consistent, whether the first surgical procedure and the second surgical procedure are consistent, and whether the first approach and the second approach are consistent may refer to whether they are semantically consistent. The situation where the expressions are inconsistent but the semantics are consistent is also considered to be consistent.

[0155] The anatomical part, resection range, surgical procedure and approach are key elements in surgery, and contain a lot of surgical details. The single comparison results corresponding to the first anatomical part, the first resection range, the first surgical procedure and the first approach can improve the accuracy of detecting whether the second surgical name in the target data is consistent with the surgical process description. Since the surgical process description can reflect the surgical operation of the patient during the actual hospitalization, it can further improve the accuracy of detecting whether the second surgical name in the target data is consistent with the actual surgery. Moreover, the single comparison results contain the corresponding reasons, which can allow users to fully understand the logical process of the large model's judgment and improve the credibility of the single comparison results.

[0156] In addition, the single comparison result corresponding to the first anatomical part includes whether the first anatomical part and the second anatomical part are consistent and the corresponding reasons, or whether the first anatomical part and the second anatomical part have an inclusion relationship and the corresponding reasons, so as to avoid misjudgment when comparing the first anatomical part and the second anatomical part due to rough and detailed descriptions of the anatomical parts, improve the accuracy of the single comparison result corresponding to the first anatomical part, and further improve the detection accuracy of whether the second operation name and the surgical process description in the detection target data are consistent.

[0157] Step 402: Obtain a comparison result based on the individual comparison results corresponding to each first key element.

[0158] In an exemplary embodiment, the comparison result may include individual comparison results corresponding to each first key element.

[0159] Multiple first key elements and multiple second key elements contain more surgical detail information. One first key element corresponds to one second key element. By comparing any first key element with any second key element corresponding to the first key element, a single comparison result corresponding to any first key element is obtained. Based on the single comparison results corresponding to each first key element, a comparison result is obtained. By comparing multiple first key elements with multiple second key elements one by one, the consistency detection result of the second operation name and the surgical process description in the target data is determined, which can improve the detection accuracy of whether the second operation name and the surgical process description in the target data are consistent. Since the surgical process description can reflect the surgical operation situation during the patient's actual hospitalization, it can further improve the detection accuracy of whether the second operation name in the target data is consistent with the actual operation.

[0160] In some other embodiments, step 103 includes: determining the semantic similarity between the first key element and the second key element; and obtaining a comparison result based on the semantic similarity.

[0161] Step 104: Based on the comparison result, determine the consistency detection result of the second operation name and the operation process description in the target data.

[0162] In some embodiments, step 104 includes:

[0163] When the comparison result satisfies the preset condition, determining that the consistency detection result of the second operation name and the operation process description in the target data is that the second operation name and the operation process description in the target data are consistent;

[0164] When the comparison result does not meet the preset condition, determining that the consistency detection result of the second operation name and the surgical procedure description in the target data is that the second operation name and the surgical procedure description in the target data are inconsistent;

[0165] The preset conditions include that the first anatomical part and the second anatomical part are consistent or have an inclusion relationship, the first resection range and the second resection range are consistent, the first surgical procedure and the second surgical procedure are consistent, and the first approach and the second approach are consistent.

[0166] Only when the first anatomical site and the second anatomical site are consistent or have an inclusion relationship, and the first resection range and the second resection range are consistent, and the first surgical procedure and the second surgical procedure are consistent, and the first approach and the second approach are consistent, the surgical code corresponding to the first surgical name and the surgical code corresponding to the second surgical name are consistent, and the second surgical name and the surgical procedure description in the target data are consistent, without low or high coding; when the comparison result does not meet the preset conditions, the second surgical name and the surgical procedure description in the target data are inconsistent, with low or high coding, and a violation occurs.

[0167] Among them, low code refers to the medical insurance payment fee corresponding to the surgical code corresponding to the second operation name in the target data, which is lower than the medical insurance payment fee corresponding to the surgical code corresponding to the first operation name in the surgical process description; high code refers to the medical insurance payment fee corresponding to the surgical code corresponding to the second operation name in the target data, which is higher than the medical insurance payment fee corresponding to the surgical code corresponding to the first operation name in the surgical process description.

[0168] It can assist hospitals in filling in surgical operation information in target data, and can also conduct post-audit to detect violations. It improves generalization, is not limited to the construction of prior knowledge, and can identify and discover more violations.

[0169] In the exemplary embodiment, the first operation name is gallbladder puncture, and the second operation name is renal puncture, wherein the anatomical part of gallbladder puncture is gallbladder, and the operation method is puncture; the anatomical part of renal puncture is kidney, and the operation method is puncture. Therefore, the anatomical parts are different, the operation methods are the same, and the codes are different.

[0170] The first operation is called pneumonectomy, and the second operation is called lobectomy. The anatomical part of pneumonectomy is the lung, the resection range is one side of the lung, the surgical procedure is resection, and the approach is thoracotomy; the anatomical part of lobectomy is the lung, the resection range is part of the lung lobe, the surgical procedure is resection, and the approach is thoracotomy. Therefore, the anatomical parts are the same, the resection range is different, the surgical procedure is the same, the approach is the same, but the codes are different.

[0171] The name of the first operation is nasal microwave cauterization hemostasis under nasal endoscope, and the name of the second operation is nasal electrocoagulation hemostasis under nasal endoscope. The anatomical site of nasal microwave cauterization hemostasis under nasal endoscope is the nasal passage, the operation method is microwave cauterization hemostasis, and the approach is under nasal endoscope; the anatomical site of nasal electrocoagulation hemostasis under nasal endoscope is the nasal passage, the operation method is electrocoagulation hemostasis, and the approach is under nasal endoscope. Therefore, the anatomical site is the same, the operation method is different, the approach is the same, and the coding is different.

[0172] The first operation is called partial hepatectomy, and the second operation is called laparoscopic partial hepatectomy. The anatomical part of partial hepatectomy is the liver, the resection range is a part of the liver, the surgical procedure is resection, and the approach is laparotomy; the anatomical part of laparoscopic partial hepatectomy is the liver, the resection range is a part of the liver, the surgical procedure is resection, and the approach is laparoscopy. Therefore, the anatomical part, the resection range, the surgical procedure, the approach are different, and the coding is different.

[0173] The name of the first operation is radical resection of left thyroid cancer, and the name of the second operation is laparoscopic total thyroidectomy. The first anatomical site is the neck, the first resection range is the left lobe of the thyroid gland, the first surgical procedure is resection, and the first approach is the neck incision. The second anatomical site is the neck, especially one side of the thyroid gland, the second resection range is the entire thyroid gland, the second surgical procedure is resection, and the second approach is laparoscope. Therefore, there is an inclusion relationship between the anatomical sites, the resection range is different, the surgical procedures are the same, the approaches are different, and the codes are different.

[0174] In an exemplary embodiment, when the result of the consistency check between the second operation name and the surgical procedure description in the target data is that the second operation name and the surgical procedure description in the target data are consistent, the review is passed; when the result of the consistency check between the second operation name and the surgical procedure description in the target data is that the second operation name and the surgical procedure description in the target data are inconsistent, a violation is prompted.

[0175] In some embodiments, the surgical procedure description includes at least one first surgical name, and the target data includes at least one second surgical name. It can be first determined whether each first surgical name and each second surgical name are semantically similar; the semantically similar first surgical names and second surgical names are combined into a surgical name pair, wherein a surgical name pair includes a semantically similar first surgical name and a second surgical name; it is determined whether there are other first surgical names in the first surgical name extracted from the surgical procedure description except the first surgical name in the surgical name pair; it is determined whether there are other second surgical names in the second surgical name in the target data except the second surgical name in the surgical name pair; based on the other first surgical names and the other second surgical names, it is determined whether there is overwriting or underwriting; the first key elements and the second key elements corresponding to the surgical name pair are compared to obtain a comparison result, based on the comparison result, a consistency detection result of the second surgical name and the first surgical name in the surgical name pair is determined, and based on the consistency detection result of the second surgical name and the first surgical name in the surgical name pair, it is determined whether there is a high-level or low-level code.

[0176] In an exemplary embodiment, whether each first surgical operation name and each second surgical operation name are semantically similar can be determined by comparing them through semantic similarity, or they can be directly input into a large model for comparison.

[0177] In the exemplary embodiment, overwriting means that the second operation name in the target data has more than the actual operation; underwriting means that the second operation name in the target data has less than the actual operation. Low coding means that the medical insurance payment fee corresponding to the operation code corresponding to the second operation name in the target data is lower than the medical insurance payment fee corresponding to the operation code corresponding to the first operation name in the surgical process description; high coding means that the medical insurance payment fee corresponding to the operation code corresponding to the second operation name in the target data is higher than the medical insurance payment fee corresponding to the operation code corresponding to the first operation name in the surgical process description.

[0178] It can identify overwriting, underwriting, low editing and high editing, and can identify and discover more violations.

[0179] In an exemplary embodiment, based on other first surgical names and other second surgical names, it is determined whether there is overwriting or underwriting. It may be that there is a first surgical name among other first surgical names, but this surgical name is not included in the target data, indicating that the second surgical name in the target data is less written than the actual surgery. It may also be that there is a surgical name among other second surgical names, and it can be determined whether this surgical name needs to be written with a surgical procedure description based on the surgical name and predefined rules. If the surgical procedure description needs to be written, but this surgical name is not included in the surgical procedure description, then the second surgical name in the target data is more written than the actual surgery.

[0180] In some embodiments, the surgical procedure description includes at least one first surgical name, and the target data includes at least one second surgical name. The first key element corresponding to any first surgical name and the second key element corresponding to any second surgical name can be compared to obtain a comparison result corresponding to any surgical name combination, wherein a surgical name combination includes a first surgical name and a second surgical name; based on the comparison result corresponding to the surgical name combination, it is determined whether there is any violation.

[0181] It is not necessary to determine in advance whether the first operation names and the second operation names are semantically similar. Instead, the first key element corresponding to any first operation name and the second key element corresponding to any second operation name can be directly compared to obtain the comparison result corresponding to any combination of operation names. Based on the comparison result corresponding to the combination of operation names, it is determined whether there is any violation. The first key element and the second key element contain more detailed operation information, which can more accurately determine whether there is any violation.

[0182] In summary, in the present application, the first key element corresponding to the first operation name in the surgical procedure description is extracted, the second key element corresponding to the second operation name in the target data is extracted, the first key element and the second key element are compared to obtain a comparison result, and based on the comparison result, the consistency detection result of the second operation name in the target data and the surgical procedure description is determined. The first key element and the second key element contain more surgical detail information. By comparing the first key element and the second key element, the consistency detection result of the second operation name in the target data and the surgical procedure description is determined. Compared with directly comparing the first operation name and the second operation name, the detection accuracy of whether the second operation name in the target data and the surgical procedure description are consistent can be improved. Since the surgical procedure description can reflect the surgical operation of the patient during the actual hospitalization process, the detection accuracy of whether the second operation name in the target data is consistent with the actual operation can be further improved.

[0183] Exemplary Devices

[0184] Accordingly, the present application also provides a surgical consistency detection device, such as Figure 6 As shown, the surgical consistency detection device includes:

[0185] A first extraction unit 601 is used to extract a first key element corresponding to a first surgery name in the surgical procedure description;

[0186] The second extraction unit 602 is used to extract the second key element corresponding to the second surgery name in the target data;

[0187] A comparison unit 603 is used to compare the first key element and the second key element to obtain a comparison result;

[0188] The detection unit 604 is used to determine a consistency detection result between the second operation name in the target data and the description of the operation process based on the comparison result.

[0189] Optionally, the first extraction unit 601 is specifically configured to:

[0190] Based on the description of the surgical procedure, a first prompt word is generated;

[0191] Inputting the first prompt word into the large model to obtain a first key element corresponding to the first surgery name in the surgical procedure description;

[0192] The first prompt word is used to instruct the large model to extract the first key element corresponding to the first operation name in the description of the surgical procedure.

[0193] Optionally, the second extraction unit 602 is specifically configured to:

[0194] generating a second prompt word based on the second surgery name in the target data;

[0195] Inputting the second prompt word into the large model to obtain a second key element corresponding to the second surgery name in the target data;

[0196] The second prompt word is used to indicate that the large model extracts a second key element corresponding to the second surgery name in the target data.

[0197] Optionally, the first surgery name corresponds to a plurality of first key elements, the second surgery name corresponds to a plurality of second key elements, and one first key element corresponds to one second key element;

[0198] The comparison unit 603 includes:

[0199] A comparison subunit, used to compare any one of the first key elements with a second key element corresponding to the first key element, and obtain a single comparison result corresponding to the first key element;

[0200] The processing subunit is used to obtain the comparison result based on the single comparison results corresponding to each of the first key elements.

[0201] Optionally, the comparison subunit is specifically used for:

[0202] Generate a third prompt word based on any one of the first key elements and a second key element corresponding to the any one of the first key elements;

[0203] Inputting the third prompt word into the large model to obtain a single comparison result corresponding to any one of the first key elements;

[0204] The third prompt word is used to instruct the large model to compare any one of the first key elements with the second key element corresponding to the any one of the first key elements, and obtain a single comparison result corresponding to the any one of the first key elements.

[0205] Optionally, the first key element includes a first anatomical site, a first resection range, a first surgical procedure and a first approach; the second key element includes a second anatomical site, a second resection range, a second surgical procedure and a second approach;

[0206] The single comparison result corresponding to the first anatomical part includes whether the first anatomical part and the second anatomical part are consistent and the corresponding reason, or whether the first anatomical part and the second anatomical part have an inclusion relationship and the corresponding reason;

[0207] The single comparison result corresponding to the first resection range includes whether the first resection range is consistent with the second resection range and the corresponding reasons;

[0208] The single comparison result corresponding to the first surgical procedure includes whether the first surgical procedure is consistent with the second surgical procedure and the corresponding reasons;

[0209] The single comparison result corresponding to the first approach includes whether the first approach is consistent with the second approach and the corresponding reason.

[0210] Optionally, the detection unit 604 is specifically configured to:

[0211] In the case where the comparison result satisfies a preset condition, determining that a consistency detection result of the second operation name in the target data and the surgical procedure description is that the second operation name in the target data and the surgical procedure description are consistent;

[0212] In the case where the comparison result does not satisfy the preset condition, determining that the consistency detection result of the second operation name in the target data and the surgical procedure description is that the second operation name in the target data and the surgical procedure description are inconsistent;

[0213] Among them, the preset conditions include that the first anatomical part and the second anatomical part are consistent or have an inclusion relationship, and the first resection range and the second resection range are consistent, and the first surgical procedure and the second surgical procedure are consistent, and the first approach and the second approach are consistent.

[0214] Optionally, the target data includes at least one of a medical record cover page and a settlement list.

[0215] The surgical consistency detection device provided in this embodiment belongs to the same application concept as the surgical consistency detection method provided in the above embodiments of this application, and can execute the surgical consistency detection method provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects of executing the surgical consistency detection method. For technical details not fully described in this embodiment, please refer to the specific processing content of the surgical consistency detection method provided in the above embodiments of this application, and will not be repeated here.

[0216] The functions implemented by the above-mentioned first extraction unit 601, second extraction unit 602, comparison unit 603 and detection unit 604 may be implemented by the same or different processors respectively, which is not limited in the embodiment of the present application.

[0217] It should be understood that the units in the above devices can be implemented in the form of a processor calling software. For example, the device includes a processor, the processor is connected to a memory, and instructions are stored in the memory. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each unit of the device, wherein the processor can be a general-purpose processor, such as a CPU or a microprocessor, etc., and the memory can be a memory in the device or a memory outside the device. Alternatively, the units in the device can be implemented in the form of hardware circuits, and the functions of some or all units can be realized by designing the hardware circuits. The hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are realized by designing the logical relationship of the components in the circuit; for another example, in another implementation, the hardware circuit can be implemented by PLD, taking FPGA as an example, which can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by the configuration file, so as to realize the functions of some or all of the above units. All units of the above devices can be implemented in the form of a processor calling software, or in the form of hardware circuits, or in part by a processor calling software, and the remaining part is implemented in the form of hardware circuits.

[0218] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and run instructions, such as a CPU, a microprocessor, a GPU, or a DSP; in another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.

[0219] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0220] In addition, all or part of the units in the above device can be integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a SOC. The SOC may include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The type of the at least one processor may be different, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0221] Exemplary Electronic Devices

[0222] An embodiment of the present application provides an electronic device, see Figure 7 As shown, the device includes:

[0223] Memory 200 and processor 210;

[0224] The memory 200 is connected to the processor 210 and is used to store programs;

[0225] The processor 210 is used to implement the surgical consistency detection method disclosed in any of the above embodiments by running the program stored in the memory 200.

[0226] Specifically, the electronic device may further include: a bus, a communication interface 220 , an input device 230 and an output device 240 .

[0227] The processor 210, the memory 200, the communication interface 220, the input device 230 and the output device 240 are connected to each other via a bus.

[0228] A bus may include a pathway that transfers information between components of a computer system.

[0229] The processor 210 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the scheme of the present invention. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0230] The processor 210 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0231] The memory 200 stores a program for executing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes a computer operation instruction. More specifically, the memory 200 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0232] The input device 230 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0233] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0234] The communication interface 220 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0235] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement each step of any surgical consistency detection method provided in the above embodiments of the present application.

[0236] Exemplary computer program products and storage media

[0237] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the surgical consistency detection method according to various embodiments of the present application described in any of the above embodiments of this specification.

[0238] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0239] In addition, the embodiment of the present application may also be a storage medium on which a computer program is stored. The computer program is executed by a processor to execute the steps of the surgical consistency detection method according to various embodiments of the present application described in any of the above embodiments of this specification, and specifically the following steps may be implemented:

[0240] Step 101: extracting a first key element corresponding to a first operation name in a description of an operation procedure.

[0241] Step 102: extracting a second key element corresponding to a second operation name in the target data.

[0242] Step 103: compare the first key element and the second key element to obtain a comparison result.

[0243] Step 104: Based on the comparison result, determine the consistency detection result of the second operation name and the operation process description in the target data.

[0244] For the aforementioned method embodiments, for the sake of simplicity, they 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 order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0245] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0246] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0247] The modules and sub-modules in the devices and terminals in the various embodiments of the present application can be combined, divided and deleted according to actual needs.

[0248] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple submodules or modules can be combined or integrated into another module, 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 an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0249] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0250] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.

[0251] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0252] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0253] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0254] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A surgical consistency detection method, characterized in that: include: Extracting the first key element corresponding to the first surgery name in the surgical procedure description; Extracting a second key element corresponding to a second surgery name in the target data; Comparing the first key element and the second key element to obtain a comparison result; Based on the comparison result, a consistency detection result between the second operation name in the target data and the description of the operation procedure is determined.

2. The surgical consistency detection method according to claim 1, characterized in that: The step of extracting the first key element corresponding to the first surgery name in the surgical procedure description includes: Based on the description of the surgical procedure, a first prompt word is generated; Inputting the first prompt word into the large model to obtain a first key element corresponding to the first surgery name in the surgical procedure description; The first prompt word is used to instruct the large model to extract the first key element corresponding to the first operation name in the description of the surgical procedure.

3. The surgical consistency detection method according to claim 1, characterized in that: The second key element corresponding to the second surgery name in the extracted target data includes: generating a second prompt word based on the second surgery name in the target data; Inputting the second prompt word into the large model to obtain a second key element corresponding to the second surgery name in the target data; The second prompt word is used to indicate that the large model extracts a second key element corresponding to the second surgery name in the target data.

4. The surgical consistency detection method according to claim 1, characterized in that: The first operation name corresponds to a plurality of first key elements, the second operation name corresponds to a plurality of second key elements, and one first key element corresponds to one second key element; The comparing the first key element and the second key element to obtain a comparison result includes: Comparing any one of the first key elements with a second key element corresponding to the first key element, and obtaining a single comparison result corresponding to the first key element; A comparison result is obtained based on the individual comparison results corresponding to each first key element.

5. The surgical consistency detection method according to claim 4, characterized in that: The comparing any one of the first key elements with the second key element corresponding to the any one of the first key elements to obtain a single comparison result corresponding to the any one of the first key elements includes: Generate a third prompt word based on any one of the first key elements and a second key element corresponding to the any one of the first key elements; Inputting the third prompt word into the large model to obtain a single comparison result corresponding to any one of the first key elements; The third prompt word is used to instruct the large model to compare any one of the first key elements with the second key element corresponding to the any one of the first key elements, and obtain a single comparison result corresponding to the any one of the first key elements.

6. The surgical consistency detection method according to claim 4, characterized in that: The first key element includes a first anatomical site, a first resection range, a first surgical procedure and a first approach; the second key element includes a second anatomical site, a second resection range, a second surgical procedure and a second approach; The single comparison result corresponding to the first anatomical part includes whether the first anatomical part and the second anatomical part are consistent and the corresponding reason, or whether the first anatomical part and the second anatomical part have an inclusion relationship and the corresponding reason; The single comparison result corresponding to the first resection range includes whether the first resection range is consistent with the second resection range and the corresponding reasons; The single comparison result corresponding to the first surgical procedure includes whether the first surgical procedure is consistent with the second surgical procedure and the corresponding reasons; The single comparison result corresponding to the first approach includes whether the first approach is consistent with the second approach and the corresponding reason.

7. The surgical consistency detection method according to claim 6, characterized in that: Determining the consistency detection result between the second operation name in the target data and the operation process description based on the comparison result includes: In the case where the comparison result satisfies a preset condition, determining that a consistency detection result of the second operation name in the target data and the surgical procedure description is that the second operation name in the target data and the surgical procedure description are consistent; In the case where the comparison result does not satisfy the preset condition, determining that the consistency detection result of the second operation name in the target data and the surgical procedure description is that the second operation name in the target data and the surgical procedure description are inconsistent; Among them, the preset conditions include that the first anatomical part and the second anatomical part are consistent or have an inclusion relationship, and the first resection range and the second resection range are consistent, and the first surgical procedure and the second surgical procedure are consistent, and the first approach and the second approach are consistent.

8. The surgical consistency detection method according to any one of claims 1 to 7, characterized in that: The target data includes at least one of a medical record cover page and a settlement list.

9. A surgical consistency detection device, characterized in that: include: A first extraction unit, used to extract a first key element corresponding to a first surgery name in the surgical procedure description; A second extraction unit is used to extract a second key element corresponding to a second surgery name in the target data; A comparison unit, used for comparing the first key element and the second key element to obtain a comparison result; A detection unit is used to determine a consistency detection result between the second operation name in the target data and the description of the operation process based on the comparison result.

10. An electronic device, characterized in that: including memory and processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the surgical consistency detection method as described in any one of claims 1 to 8 by running the program in the memory.

11. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the surgical consistency detection method according to any one of claims 1 to 8 is implemented.

12. A computer program product, characterized in that The method comprises computer program instructions, which, when executed by a processor, enable the processor to perform the surgical consistency detection method according to any one of claims 1 to 8.

Images