WO2020034808A1

WO2020034808A1 - Decision data acquisition method and apparatus, computer device, and storage medium

Info

Publication number: WO2020034808A1
Application number: PCT/CN2019/096970
Authority: WO
Inventors: 胡帆; 程吉安
Original assignee: 平安医疗健康管理股份有限公司
Priority date: 2018-08-14
Filing date: 2019-07-22
Publication date: 2020-02-20
Also published as: CN109509102A; CN109509102B

Abstract

A decision data acquisition method, comprising: acquiring data of the state of injury of an injured person to be compensated, and obtaining the corresponding anatomical site information according to the data of the state of injury; acquire, from a pre-established semantic network, a lesion corpus set associated with the anatomical site information, and sending a first option information set to a terminal according to the lesion corpus set; receiving a first selection result sent by the terminal, searching for a corresponding injury severity condition corpus set from the semantic network according to the first selection result, and sending a second option information set to the terminal according to the injury severity corpus set; receiving a second selection result returned from the terminal, and acquiring, from a preset matched data set, target matched data according to the anatomical site information, the first selection result, and the second selection result; and acquiring preset claim settlement data corresponding to the target matched data, obtaining target decision data according to the claim settlement data, and sending the target decision data to the terminal.

Description

Decision data acquisition method, device, computer equipment and storage medium

Cross-reference to related applications

This application claims the priority of a Chinese patent application filed on August 14, 2018, with the application number 2018109245498, and the application name is "claims decision method, device, computer equipment, and storage medium", the entire contents of which are incorporated by reference. In this application.

Technical field

The present application relates to a method, an apparatus, a computer device, and a storage medium for acquiring decision data.

Background technique

With the rapid development of computer technology, more and more occasions can be applied to computer technology. For example, in a personal injury claim during a car accident, a computer can be used to obtain claim decision data to assist the claim decision.

In traditional technology, computer equipment usually collects historical injury data and corresponding historical decision data in advance to obtain claims decision data. Based on these data, a database is established. When claim decision data needs to be obtained, computer equipment first needs to find the The historical injury data is similar to the injury data, so as to obtain the corresponding historical claims data as the current claims decision data. However, the inventor realized that the historical collected data continuously accumulated over time. When the amount of data in the database reached a certain amount In this way, since the entire database needs to be traversed to find historical injury data, a lot of computer resources are wasted.

Summary of the Invention

According to various embodiments disclosed in the present application, a method, an apparatus, a computer device, and a storage medium for acquiring decision data are provided.

A method for obtaining decision data includes: obtaining injury data of an injured person to be compensated, and obtaining corresponding anatomical site information according to the injury data; and acquiring a lesion associated with the anatomical site information from a pre-established semantic network A corpus set, sending a first option information set to a terminal according to the diseased corpus set; receiving a first selection result returned by the terminal according to the first option information set, and from the semantic network according to the first selection result Searching for a corresponding injury severity corpus, and sending a second option information set to the terminal according to the injury severity corpus; receiving a second selection result returned by the terminal according to the second option information set, according to all The anatomical part information, the first selection result, and the second selection result obtain target matching data corresponding to the injured person to be compensated from a preset matching data set, and obtain a preset claim corresponding to the target matching data. Data, obtain target decision data according to the preset claim data, and send the target decision data to Said terminal.

A decision data acquisition device includes:

An injury data acquisition module, configured to acquire injury data of an injured person to be compensated, and obtain corresponding anatomical site information according to the injury data;

A first option information set sending module, configured to obtain a lesion corpus set associated with the anatomical site information from a pre-established semantic network, and send a first option information set to a terminal according to the lesion corpus set;

A second option information set sending module is configured to receive a first selection result returned by the terminal according to the first option information set, and search for a corresponding injury severity corpus from the semantic network according to the first selection result. Sending a second option information set to the terminal according to the injury severity corpus;

The target matching data acquisition module is configured to receive a second selection result returned by the terminal according to the second option information set, and select a preset selection result from the anatomical part information, the first selection result, and the second selection result. To obtain target matching data corresponding to the injured person to be compensated from the matching data set; and

The target decision data sending module is configured to obtain preset claim data corresponding to the target matching data, obtain target decision data according to the preset claim data, and send the target decision data to the terminal.

A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the one or more processors are executed. The following steps: obtain the injury data of the injured person to be compensated, and obtain the corresponding anatomical site information according to the injury data; obtain a lesion corpus set associated with the anatomical site information from a pre-established semantic network, and The disease corpus set sends a first option information set to the terminal; receives a first selection result returned by the terminal according to the first option information set, and searches for a corresponding injury from the semantic network according to the first selection result A severity corpus, sending a second option information set to the terminal according to the injury severity corpus; receiving a second selection result returned by the terminal according to the second option information set, according to the anatomical site information, Obtaining the first selection result and the second selection result from a preset matching data set Corresponding target data matching the injured; acquiring the matching data corresponding to a preset target claims data, decisions to obtain the target data according to the preset claims data, and transmits the decision data to the target terminal.

One or more non-volatile computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors perform the following steps: obtaining pending claims The injury data of the person, and obtain the corresponding anatomical site information according to the injury data; obtain a lesion corpus set associated with the anatomical site information from a pre-established semantic network, and provide the terminal to the terminal according to the lesion corpus set Send a first option information set; receive a first selection result returned by the terminal according to the first option information set, and find a corresponding injury severity corpus from the semantic network according to the first selection result, The injury severity corpus sends a second option information set to the terminal; receives a second selection result returned by the terminal according to the second option information set, according to the anatomical site information, the first selection result, Obtaining, by the second selection result, a target matching number corresponding to the injured person to be compensated from a preset matching data set ; Acquiring the matching data corresponding to a preset target claims data, decisions to obtain the target data according to the preset claims data, and transmits the decision data to said target terminal.

Details of one or more embodiments of the present application are set forth in the accompanying drawings and description below. Other features and advantages of the application will become apparent from the description, the drawings, and the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to explain the technical solutions in the embodiments of the present application more clearly, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. Those of ordinary skill in the art can obtain other drawings according to the drawings without paying creative labor.

FIG. 1 is an application scenario diagram of a method for acquiring decision data according to one or more embodiments; FIG.

2 is a schematic flowchart of a method for acquiring decision data according to one or more embodiments;

3 is a schematic flowchart of steps for generating a semantic network according to one or more embodiments;

FIG. 4 is a structural block diagram of a decision data acquisition device according to one or more embodiments; FIG.

FIG. 5 is an internal structural diagram of a computer device according to one or more embodiments.

detailed description

In order to make the technical solution and advantages of the present application more clear and clear, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application.

The method for obtaining decision data provided in this application can be applied to the application environment shown in FIG. 1, and includes a terminal 102 and a server 104. The terminal 102 is a terminal used by a claim adjuster to make a claim decision. The terminal 102 performs communication with the server 104 through the network. Communication. The server 104 obtains the injury data of the injured person, determines the anatomical part corresponding to the injury of the patient according to the injury data, and then obtains a set of lesion corpora associated with the anatomical part from a pre-established semantic network. The loss corpus set sends the first option information set to the terminal. The claim adjuster can select the option that best matches the patient's injury through the terminal 102, and then sends the selection result to the server 104 through the terminal. After the server 104 receives the selection result, it As a result, the corresponding degree corpus set is found from the semantic network, and the second option information set is sent to the terminal according to the degree corpus. The claimant again selects the option that best matches the patient's injury through the terminal 102, and then sends the selection result to the server through the terminal. 104. After receiving the selection result, the server 104 obtains target matching data from a preset matching data set according to the anatomical part and the two selection results, queries the corresponding preset claim data according to the matching data, and obtains the preset claim data. Target decision data, send target decision data Terminal 102.

The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, and tablet computers. The server 104 may be implemented by an independent server or a server cluster composed of multiple servers.

In some embodiments, as shown in FIG. 2, a method for acquiring decision data is provided. The method is applied to the server in FIG. 1 as an example, and includes the following steps:

Step S202: Acquire injury data of the injured person to be compensated, and obtain corresponding anatomical part information according to the injury data.

Specifically, the injury data refers to data related to the injury situation of the patient, including but not limited to pictures, text or speech. Anatomical part refers to the medical description of various parts of the human body anatomy.

In this embodiment, the claim adjuster may send the injury data to the server through the terminal after knowing the general injury situation of the injured person to be compensated. The injury data may be text or voice describing the injured part of the injured person, or a picture of the injured part of the injured person. After receiving the injury data, the server can determine the anatomical part corresponding to the injured part of the patient according to the injury data.

In some embodiments, when the injury data is a text description of the injured part, keywords can be extracted from the text description, the extracted keywords can be matched with the keyword set corresponding to each anatomical part, and the key to successful matching is The anatomical part corresponding to the word is used as the anatomical part corresponding to the injury data; when the injury data is speech data, the speech data can be converted into text, and then keywords are extracted, and the extracted keywords correspond to the keywords of each anatomical part. The set is used for matching, and the anatomical part corresponding to the successfully matched keywords is used as the anatomical part corresponding to the injury data.

In another embodiment, the injury data may be picture data corresponding to the injured part of the injured person, and the server may input the picture data into a trained machine learning model that can be used for classification, and finally obtain the corresponding data of the injury data. Anatomy.

Step S204: Obtain a lesion corpus set associated with anatomical site information from a pre-established semantic network, and send a first option information set to the terminal according to the lesion corpus set.

Specifically, the semantic network is a form of expressing medical knowledge structure in a network format. The semantic network in this embodiment includes at least an anatomical site corpus, injury severity corpus, and lesion corpus, among various corpora. A certain association relationship is established according to a preset rule, and two corpora with the association relationship are connected through a "edge" in the network in the semantic network. In the semantic network, related corpora of any corpus can be found through these "edges". Anatomical corpus refers to the description of various anatomical parts in human anatomy, such as hips, coccyx, etc .; lesion corpus refers to the medical description of injuries caused by injuries to anatomical parts, such as fractures, bleeding, dislocation, etc. ; Severity refers to the medical description of the severity of the injury, for example, comminuted, open, semi, and so on.

In this embodiment, after obtaining the anatomical site information corresponding to the injury data, the server can traverse all the anatomical site corpora in the semantic tree, and then locate the anatomical site corpus. After locating the anatomical site information, In the semantic network, all the diseased corpora associated with it are found. These diseased corpuses form a diseased corpus, and then send a first option information set to the terminal according to the diseased corpus. The first option information set refers to option information related to the damaged corpus provided to the terminal for selection.

In some embodiments, the first option information set may directly be a set composed of each lesion corpus in the lesion corpus.

Step S206: The receiving terminal according to the first selection result returned by the first option information set, finds the corresponding injury severity corpus from the semantic network according to the first selection result, and sends the second option information set to the terminal according to the injury severity corpus. .

Specifically, after the server sends the first set of option information to the terminal, the terminal displays the option information, and the adjuster can select on the terminal according to the actual injury of the patient, and then the terminal uses the option information selected by the adjuster as the selection result. Send to server. Since each option in the first option information is related to the lesion corpus in the lesion corpus, when the server receives the selection result of the terminal, it can obtain the lesion corpus corresponding to the selection result, and then in the semantic network Locate the lesion corpus, and obtain all the severity corpora corresponding to the lesion corpus, and then send a second option information set to the terminal according to these severity corpora; the second option information set refers to the selection provided to the terminal for selection Option information related to injury severity corpus.

In some embodiments, the second option information set may directly be a set composed of each injury severity corpus in the injury severity corpus.

Step S208: The receiving terminal obtains the target matching data corresponding to the person to be injured from the preset matching data set according to the second selection result returned by the second option information set, and according to the anatomical part information, the first selection result, and the second selection result. .

Specifically, after the server sends the second set of option information to the terminal, the terminal displays these option information, and the adjuster can select on the terminal according to the actual injury of the patient, and then the terminal uses the option information selected by the adjuster as the selection result. Send to server. Since each option in the second option information is related to the injury severity corpus in the injury severity corpus, when the server receives the selection result of the terminal, it can obtain the injury severity corpus corresponding to the selection result.

The preset matching data set refers to a set composed of preset matching data. The matching data refers to describing an injury situation of an injured person from one or more dimensions of anatomy, damage, and severity of the injury. Data, such as "comminuted fracture of the left index finger", "open cerebellar hemorrhage", and "severe dislocation of the right hip joint" After the injury severity corpus, you can calculate the matching degree between the corpus and each matching data in the matching data set, and select the matching data as the target matching data corresponding to the injured person according to the calculation result of the matching degree. For example, each match can be calculated. The matching score between the data and the above corpora, and then select the one with the highest matching score as the target matching data.

Step S210: Obtain preset claim data corresponding to the target matching data, obtain target decision data according to the preset claim data, and send the target decision data to the terminal.

Specifically, the preset claim data includes, but is not limited to, a claim amount and a claim time limit. The preset claim data is manually set in advance.

In this embodiment, for each matching data in the matching data set, corresponding preset claim data is set. After the server obtains the target matching data, it queries the preset claim data corresponding to the target matching data, and then obtains the target decision data based on the queryed preset claim data. The target decision data refers to the treatment obtained by the server from the preset claim data. The final decision data of the claims patient. Further, the server sends the target decision data to the terminal.

It can be understood that there may be one or more preset claims data corresponding to each matching data. When there is only one claim data, the preset claims data is directly used as the target decision data; when there are multiple preset claims data The server selects one of these claims data as the target decision data.

In the above method for obtaining decision data, the server determines the anatomical part corresponding to the injury of the patient after obtaining the injury data of the person to be compensated, and then finds the lesion corpus from the semantic network and sends the option information to the terminal. , And then the server further finds the severity corpus from the semantic network according to the selection result returned by the terminal, and sends the option information to the terminal again, and after receiving the selection result returned by the terminal again, it can select the matching data set based on all the acquired data. Determine the target matching data and finally get the target decision data. Since it is no longer necessary to traverse the database, you can find the data directly from the semantic network and the target matching data collection. The semantic network and target matching data will not change over time. Accumulation, therefore, when the amount of data in the database reaches a certain level, the method of the present application can significantly save computer resources compared to traditional techniques.

In some embodiments, acquiring the injury data of the injured person to be compensated, and obtaining the corresponding anatomical part information according to the injury data, includes: receiving the injury picture of the injured person to be sent from the receiving terminal; and inputting the injury picture to the trained person. In the convolutional neural network, the anatomical part information corresponding to the injury picture is obtained.

Specifically, the trained convolutional neural network includes a convolutional layer, a pooling layer, and a fully connected layer; the injury picture is input into the trained convolutional neural network to obtain the anatomical part information corresponding to the injury picture, specifically Including: taking the injury picture of the patient to be claimed as the input of the convolution layer, the convolution layer is used to perform a convolution operation on the image data corresponding to the patient to be claimed to obtain the first feature matrix; and using the first feature matrix as the input of the pooling layer The pooling layer is used to project the largest weight in each vector in the first feature matrix to obtain a normalized second feature matrix; the second feature matrix is used as the input of the fully connected layer, and the fully connected layer is used to The second feature matrix is classified and calculated to obtain anatomical site information.

The convolutional neural network can be obtained by training: obtaining the training sample set and the anatomical part information corresponding to each training sample in the training sample set; each training sample in the training sample set is used as the input of the convolutional neural network in turn, and its corresponding The anatomical part information is used as the expected output of the convolutional neural network to train the convolutional neural network to obtain the currently trained convolutional neural network. The training sample refers to historical injury picture data whose anatomical site information has been determined.

In some embodiments, as shown in FIG. 3, before step S204, a step of generating a semantic tree is further included, which specifically includes:

Step S302: Obtain a semantic tree of a preset dimension, where the preset dimension includes at least anatomy site, lesion, and severity of injury.

Specifically, firstly, a corpus of each preset dimension is extracted from a standardized medical corpus, and a semantic tree is constructed in advance according to the semantic relationship between the corpora corresponding to each dimension. Each node in the semantic tree is a standardized medical word. The medical corpus can be, for example, an ICD (International Classification of Diseases) coding system, and the preset dimensions include at least the anatomical part, the lesion, and the severity of the injury. As shown in Table 1 below, an example of a partial semantic tree for the part “ear” is given:

Table 1

As can be seen from the above table, the semantic tree can have a multi-level structure. The higher the level, the more detailed the medical term for the semantic node term "ear" corresponding to the root node.

In step S304, the co-occurrence frequency between the node corresponding to the semantic tree of each dimension and the node corresponding to the semantic tree of other dimensions is calculated.

Specifically, for the semantic tree of each dimension, the co-occurrence frequency between each node corresponding to the semantic tree of the other dimension and the nodes corresponding to the semantic tree of other dimensions is calculated. The co-occurrence frequency refers to the two words in a preset context range. The frequency of co-occurrence within a group. The greater the co-occurrence frequency, the greater the degree of correlation between the two words. The co-occurrence frequency is often expressed in the form of a co-occurrence matrix. For example, the co-occurrence matrix can be calculated by using a pair algorithm or a stripes algorithm implemented by a MapReduce model.

Step S306: Establish an association between two nodes whose co-occurrence frequency is greater than a preset threshold to generate a semantic network.

Specifically, the preset threshold may be set to different degrees according to different requirements on the degree of association between two interrelated nodes in the semantic network. The higher the degree of correlation between two interrelated nodes is, the larger the preset threshold is.

In this embodiment, two nodes whose co-occurrence frequency is greater than a preset threshold are connected by one edge in the semantic network, that is, an association relationship is established between the corpora corresponding to the two nodes. When the relationship between the semantic trees is established, the semantic network is obtained. In this semantic network, searching through any corpus can obtain all the corpora associated with it.

Since the semantic network generated in this embodiment establishes the co-occurrence relationship between the semantic trees of each dimension, it can be accurately and quickly used for corpus search and improve the efficiency of claims decision-making.

In some embodiments, obtaining the target matching data corresponding to the injured person from a preset matching data set according to the anatomical part information, the first selection result, and the second selection result includes: obtaining the anatomical part information and the first selection result respectively. And the weight corresponding to the second selection result; calculate the matching degree of the anatomical part information, the first selection result, and the second selection result to each matching data respectively; calculate the matching score corresponding to each matching data according to the weight and the matching degree, and obtain The matching data with the highest matching score is used as the target matching data.

In this embodiment, corresponding weights are set in advance for corpora in three dimensions of anatomical site, lesion, and severity of injury, and because the first selection result is selected from the first option information set related to the lesion corpus It is obtained that, therefore, the weight of the first selection result is the same as the weight of the diseased corpus. Similarly, the weight of the second selection result is the same as the weight of the injury severity corpus.

In some embodiments, when calculating the matching degree of the anatomical part, the first selection result, and the second selection result with each matching data, the matching data is first segmented, and then part-of-speech tagging is performed to mark the anatomy part, the lesion, and the injury. Severity and other parts of speech, then match the anatomical part information obtained by the server with the anatomical part words of the matching data, match the first selection result obtained by the server with the lesion word of the matching data, and match the second selection result with The injury severity words of the data were matched.

The matching score is the cumulative value of the product of each matching degree and the corresponding weight. For example, if the weights of anatomical parts, lesions, and injuries are set to 0.6, 0.4, and 0.2 respectively, for a certain diagnostic data, the matching degree obtained based on the anatomical site is 0.8, and the matching degree obtained based on the disease is 0.5. According to the severity of the injury, the matching degree is 0.6, and the final matching score is 0.6x0.8 + 0.4x0.5 + 0.2x0.6.

In some embodiments, step S204 includes: for each lesion corpus in the lesion corpus, searching for corresponding description information from the description information set; obtaining the first option information according to the description information corresponding to each lesion corpus set.

Specifically, the description information refers to a popular description language corresponding to the lesion corpus. Since each corpus in the semantic network is a standardized medical description, for a claim adjuster, it is necessary to accurately understand all the lesion corpora, which requires high medical expertise. Therefore, each lesion corpus can be set in advance Corresponding descriptive information, and establish a mapping relationship between the descriptive information and the lesion corpus. After the server obtains the set of lesion corpora corresponding to the person to be compensated, the server can find the description information corresponding to each lesion corpus according to the mapping relationship. , And finally use the description information as an option to obtain a first option information set.

In this embodiment, the description information corresponding to the lesion corpus is obtained to obtain the first selection information set. Since the description information is a plain language description, the requirement for medical expertise of the claimant can be further reduced, thereby further reducing the previous period. Related training, and ultimately further reduce the cost of commercial claims.

It can be understood that, for the injury severity corpus, the corresponding description information can also be set in advance and a mapping relationship can be established. After obtaining the injury severity corpus corresponding to the injured person to be compensated, the severity of each injury can also be found according to the mapping relationship. Descriptive information corresponding to the corpus, and then use these descriptive information as options to obtain a second option information set.

In some embodiments, obtaining target decision data according to preset claims data includes: when the number of preset claims data is a preset amount, obtaining tag information corresponding to each piece of preset claim data, and obtaining personal information corresponding to a user identifier. Get target decision data based on tag information and personal information.

The preset number refers to a number greater than or equal to two. The label information corresponding to the preset claims data refers to the gender, age group, and city. For example, the label information of a preset claim data is "female", "30-50", "Beijing", "Shanghai", "Guangzhou"; the personal information corresponding to the user ID includes the gender, age and city of the patient to be claimed.

In this embodiment, the personal information of the patient is matched with the tag information of the claim data. When the personal information and the tag information are successfully matched, the preset claim data corresponding to the tag information is used as the target decision data. For example, the preset tag information of claim data A is "female", "30-50", "Beijing", "Shanghai", "Guangzhou", and the preset tag information of claim data B is "male", "30- 50 "," Beijing "," Shanghai "," Guangzhou "; personal information of a patient to be claimed includes: gender: female, age: 38, address: Shanghai, matching the patient to be settled as pre-set claims data A.

It should be understood that although the steps in the flowchart of FIG. 2-3 are sequentially displayed in accordance with the directions of the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless explicitly stated in this document, the execution of these steps is not strictly limited, and these steps can be performed in other orders. Moreover, at least a part of the steps in Figure 2-3 may include multiple sub-steps or stages. These sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. These sub-steps or stages The execution order of is not necessarily performed sequentially, but may be performed in turn or alternately with at least a part of another step or a sub-step or stage of another step.

In some embodiments, as shown in FIG. 4, a decision data acquisition device 400 is provided, including: injury data acquisition module 402, first option information set sending module 404, second option information set sending module 406, and target. The matching data obtaining module 408 and the target decision data sending module 410, wherein:

The injury data acquisition module 420 is configured to acquire injury data of an injured person to be compensated, and obtain corresponding anatomical site information according to the injury data;

The first option information set sending module 404 is configured to obtain a lesion corpus set associated with anatomical site information from a pre-established semantic network, and send the first option information set to the terminal according to the lesion corpus set;

The second option information set sending module 406 is configured to receive the first selection result returned by the terminal according to the first option information set, and search for a corresponding injury severity corpus from the semantic network according to the first selection result. The terminal sends a second option information set;

The target matching data acquisition module 408 is configured to receive the second selection result returned by the terminal according to the second option information set, and obtain the to-be-injured person from the preset matching data set according to the anatomical part information, the first selection result, and the second selection result. Corresponding target matching data; and

The target decision data sending module 410 is configured to obtain preset claim data corresponding to the target matching data, obtain target decision data according to the preset claim data, and send the target decision data to the terminal.

In some embodiments, the injury data acquisition module 420 is further configured to receive an injury picture of an injured person to be compensated sent by the terminal; and input the injury picture into a trained convolutional neural network to obtain a corresponding image of the injury picture. Anatomy information.

In some embodiments, the above-mentioned device further includes a semantic network generation module, which is configured to obtain a semantic tree of preset dimensions, the preset dimensions include at least anatomy, lesions, and severity of injuries; calculate the semantics of each dimension The co-occurrence frequency between the nodes corresponding to the tree and the nodes corresponding to the semantic tree of other dimensions; and establishing an association relationship between the two nodes whose co-occurrence frequency is greater than a preset threshold to generate a semantic network.

In some embodiments, the target matching data acquisition module 408 is further configured to obtain the weights corresponding to the anatomical part information, the first selection result, and the second selection result, and calculate the anatomical part information, the first selection result, the second selection result, and The matching degree of each matching data; and calculating the matching score corresponding to each matching data according to the weight and the matching degree, and obtaining the matching data with the largest matching score as the target matching data.

In some embodiments, the first option information set sending module 404 is further configured to find the corresponding description information from the description information set for each lesion corpus in the lesion corpus; and corresponding to each lesion corpus Get the first option information set.

In some embodiments, the target decision data sending module 410 is further configured to obtain tag information corresponding to each piece of preset claims data when the number of preset claims data is a preset amount; obtain personal information corresponding to a user identifier; and according to Tag information and personal information get target decision data.

For the specific limitation of the decision data acquisition device, refer to the foregoing limitation on the decision data acquisition method, which is not repeated here. Each module in the above-mentioned decision data acquisition device may be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules may be embedded in the hardware form or independent of the processor in the computer device, or may be stored in the memory of the computer device in the form of software, so that the processor calls and performs the operations corresponding to the above modules.

In some embodiments, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 5. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for operating systems and computer-readable instructions in a non-volatile storage medium. The database of the computer equipment is used to store matching data, preset claims data, and other data. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer-readable instructions are executed by a processor to implement a method for acquiring decision data.

Those skilled in the art can understand that the structure shown in FIG. 5 is only a block diagram of a part of the structure related to the solution of the application, and does not constitute a limitation on the computer equipment to which the solution of the application is applied. The specific computer equipment may be Include more or fewer parts than shown in the figure, or combine certain parts, or have a different arrangement of parts.

A computer device includes a memory and one or more processors. Computer-readable instructions are stored in the memory. When the computer-readable instructions are executed by the processor, the processor causes the one or more processors to perform the following steps: obtaining the injured person The corresponding anatomical site information according to the injury data; obtain the lesion corpus set associated with the anatomical site information from a pre-established semantic network, and send the first option information set to the terminal according to the lesion corpus set; The receiving terminal according to the first selection result returned by the first option information set, finds the corresponding injury severity corpus from the semantic network according to the first selection result, and sends the second option information set to the terminal according to the injury severity corpus; According to the second selection result returned by the second option information set, according to the anatomical part information, the first selection result, and the second selection result, the target matching data corresponding to the person to be compensated is obtained from the preset matching data set; the target matching data is obtained Corresponding preset claims data, based on preset claims Get objective data for decision making, decision-making will target data to the terminal.

In some embodiments, before acquiring a lesion corpus set associated with anatomical site information from a pre-established semantic network, the processor further implements the following steps when the computer executes computer-readable instructions: obtaining a semantic tree of a preset dimension, preset Dimensions include at least anatomical parts, lesions, and severity of injuries; calculate the co-occurrence frequency between the nodes corresponding to the semantic tree of each dimension and the nodes corresponding to the semantic trees of other dimensions; The two nodes establish an association relationship to generate a semantic network.

In some embodiments, obtaining the target matching data corresponding to the person to be injured from a preset matching data set according to the anatomical site information, the first selection result, and the second selection result includes: obtaining the anatomical site information and the first selection, respectively. Weight corresponding to the result and the second selection result; calculating the matching degree of the anatomical part information, the first selection result, the second selection result and each matching data respectively; and calculating the matching score corresponding to each matching data according to the weight and the matching degree, Get the matching data with the highest matching score as the target matching data.

In some embodiments, sending the first option information set to the terminal according to the damaged corpus set includes: for each damaged corpus in the damaged corpus, searching for corresponding description information from the description information set; according to each Descriptive information corresponding to the lesion corpus obtains a first option information set.

In some embodiments, obtaining the target decision data according to the preset claim data includes: when the number of the preset claim data is a preset amount, obtaining tag information corresponding to each piece of the preset claim data; and obtaining personal information corresponding to the user identifier. ; Get target decision data based on tag information and personal information.

One or more non-volatile computer-readable storage media storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors perform the following steps: obtaining pending claims The injury data of the person, and obtain the corresponding anatomical part information according to the injury data; obtain the lesion corpus set associated with the anatomical part information from the pre-established semantic network, and send the first option information set to the terminal according to the lesion corpus set Receiving terminal according to the first selection result returned by the first option information set, searching the corresponding injury severity corpus from the semantic network according to the first selection result, and sending the second option information set to the terminal according to the injury severity corpus; receiving According to the second selection result returned by the second option information set, the terminal obtains target matching data corresponding to the injured person from a preset matching data set according to the anatomical part information, the first selection result, and the second selection result; and obtains the target match. The preset claims data corresponding to the data, which is obtained based on the preset claims data Standard decision data, the decision data to the target terminal.

In some embodiments, before acquiring a lesion corpus set associated with anatomical site information from a pre-established semantic network, the computer-readable instructions further implement the following steps when executed by a processor: obtaining a semantic tree of a preset dimension, and Let the dimension include at least the anatomical part, the lesion, and the severity of the injury; calculate the co-occurrence frequency between the nodes corresponding to the semantic tree of each dimension and the nodes corresponding to the semantic tree of other dimensions; and make the co-occurrence frequency greater than a preset threshold Establish a relationship between the two nodes to generate a semantic network.

In some embodiments, obtaining the target matching data corresponding to the person to be injured from a preset matching data set according to the anatomical part information, the first selection result, and the second selection result includes: obtaining the anatomical part information and the first selection, respectively. Weight corresponding to the result and the second selection result; calculating the matching degree of the anatomical part information, the first selection result, and the second selection result to each matching data respectively; and calculating the matching score corresponding to each matching data according to the weight and the matching degree Get the matching data with the highest matching score as the target matching data.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by computer-readable instructions to instruct related hardware. The computer-readable instructions can be stored in a non-volatile computer. In the readable storage medium, the computer-readable instructions, when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the above embodiments can be arbitrarily combined. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, all It is considered to be the range described in this specification.

The above-mentioned embodiments only express several implementation manners of the present application, and their descriptions are more specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be noted that, for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the protection scope of this application patent shall be subject to the appended claims.

Claims

A method for obtaining decision data, including:

Obtaining injury data of the injured person to be compensated, and obtaining corresponding anatomical part information according to the injury data;

Acquiring a lesion corpus set associated with the anatomical site information from a pre-established semantic network, and sending a first option information set to a terminal according to the lesion corpus set;

Receiving a first selection result returned by the terminal according to the first option information set, and searching for a corresponding injury severity corpus from the semantic network according to the first selection result, and according to the injury severity corpus set, Sending, by the terminal, a second option information set;

Receiving a second selection result returned by the terminal according to the second option information set, and obtaining the second selection result from a preset matching data set according to the anatomical part information, the first selection result, and the second selection result Target matching data for the injured person; and

Acquiring preset claim data corresponding to the target matching data, obtaining target decision data according to the preset claim data, and sending the target decision data to the terminal.
The method according to claim 1, wherein the acquiring the injury data of the injured person to be compensated and obtaining the corresponding anatomical part information according to the injury data comprises:

Receiving an injury picture of the injured person to be claimed sent by the terminal; and

The injury picture is input into a trained convolutional neural network to obtain information about the anatomical part corresponding to the injury picture.
The method according to claim 1, wherein before the acquiring a corpus of lesions associated with the anatomical site information from a pre-established semantic network, the method further comprises:

Acquiring a semantic tree of a preset dimension, the preset dimension including at least anatomy, lesions, and severity of injuries;

Calculate the co-occurrence frequency between the nodes corresponding to the semantic tree of each dimension and the nodes corresponding to the semantic tree of other dimensions; and

An association relationship is established between the two nodes whose co-occurrence frequency is greater than a preset threshold to generate a semantic network.
The method according to claim 1, wherein the acquiring the to-be-injured person from a preset matching data set according to the anatomical part information, the first selection result, and the second selection result. Corresponding target matching data, including:

Obtaining the weights corresponding to the anatomical site information, the first selection result, and the second selection result respectively;

Calculating the degree of matching of the anatomical site information, the first selection result, and the second selection result with each matching data separately; and

Calculate a matching score corresponding to each matching data according to the weight and the matching degree, and obtain the matching data with the largest matching score as the target matching data.
The method according to claim 1, wherein the sending a first option information set to a terminal according to the disease corpus set comprises:

For each lesion corpus in the lesion corpus, searching for corresponding description information from the description information set; and

A first option information set is obtained according to the description information corresponding to each lesion corpus.
The method according to any one of claims 1 to 5, wherein the obtaining target decision data according to the preset claim data comprises:

When the number of the preset claims data is a preset amount, obtaining tag information corresponding to each piece of the preset claims data;

Obtaining personal information corresponding to the user identification; and

Obtain target decision data based on the tag information and the personal information.
A decision data acquisition device includes:

An injury data acquisition module, configured to acquire injury data of an injured person to be compensated, and obtain corresponding anatomical site information according to the injury data;

A first option information set sending module, configured to obtain a lesion corpus set associated with the anatomical site information from a pre-established semantic network, and send a first option information set to a terminal according to the lesion corpus set;

A second option information set sending module is configured to receive a first selection result returned by the terminal according to the first option information set, and search for a corresponding injury severity corpus from the semantic network according to the first selection result. Sending a second option information set to the terminal according to the injury severity corpus;

The target matching data acquisition module is configured to receive a second selection result returned by the terminal according to the second option information set, and select a preset selection result from the anatomical part information, the first selection result, and the second selection result. To obtain target matching data corresponding to the injured person to be compensated from the matching data set; and

The target decision data sending module is configured to obtain preset claim data corresponding to the target matching data, obtain target decision data according to the preset claim data, and send the target decision data to the terminal.
The device according to claim 7, further comprising a semantic network generation module, wherein the semantic network generation module is configured to obtain a semantic tree of a preset dimension, the preset dimension including at least anatomy, disease Damage and injury severity; calculating the co-occurrence frequency between the nodes corresponding to the semantic tree of each dimension and the nodes corresponding to the semantic tree of other dimensions; and establishing two nodes whose co-occurrence frequency is greater than a preset threshold Associations to generate a semantic network.
A computer device includes a memory and one or more processors. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the one or more processors, the one or more processors are Each processor performs the following steps:

Obtaining injury data of the injured person to be compensated, and obtaining corresponding anatomical part information according to the injury data;

Acquiring a lesion corpus set associated with the anatomical site information from a pre-established semantic network, and sending a first option information set to a terminal according to the lesion corpus set;

Receive a first selection result returned by the terminal according to the first option information set, find a corresponding injury severity corpus from the semantic network according to the first selection result, and Sending, by the terminal, a second option information set;

Receiving a second selection result returned by the terminal according to the second option information set, and obtaining the second selection result from a preset matching data set according to the anatomical part information, the first selection result, and the second selection result Target matching data for the injured person; and

Acquiring preset claim data corresponding to the target matching data, obtaining target decision data according to the preset claim data, and sending the target decision data to the terminal.
The computer device according to claim 9, wherein the processor further executes the following steps when executing the computer-readable instructions:

Receiving an injury picture of the injured person to be claimed sent by the terminal; and

The injury picture is input into a trained convolutional neural network to obtain information about the anatomical part corresponding to the injury picture.
The computer device according to claim 9, wherein the processor further executes the following steps when executing the computer-readable instructions:

Acquiring a semantic tree of a preset dimension, the preset dimension including at least anatomy, lesions, and severity of injuries;

Calculate the co-occurrence frequency between the nodes corresponding to the semantic tree of each dimension and the nodes corresponding to the semantic tree of other dimensions; and

An association relationship is established between the two nodes whose co-occurrence frequency is greater than a preset threshold to generate a semantic network.
The computer device according to claim 9, wherein the processor further executes the following steps when executing the computer-readable instructions:

Obtaining the weights corresponding to the anatomical site information, the first selection result, and the second selection result respectively;

Calculating the degree of matching of the anatomical site information, the first selection result, and the second selection result with each matching data separately; and

Calculate a matching score corresponding to each matching data according to the weight and the matching degree, and obtain the matching data with the largest matching score as the target matching data.
The computer device according to claim 9, wherein the processor further executes the following steps when executing the computer-readable instructions:

For each lesion corpus in the lesion corpus, searching for corresponding description information from the description information set; and

A first option information set is obtained according to the description information corresponding to each lesion corpus.
The computer device according to any one of claims 9 to 13, wherein the processor further executes the following steps when executing the computer-readable instructions:

When the number of the preset claims data is a preset amount, obtaining tag information corresponding to each piece of the preset claims data;

Obtaining personal information corresponding to the user identification; and

Obtain target decision data based on the tag information and the personal information.
One or more non-transitory computer-readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the following steps:

Obtaining injury data of the injured person to be compensated, and obtaining corresponding anatomical part information according to the injury data;

Acquiring a lesion corpus set associated with the anatomical site information from a pre-established semantic network, and sending a first option information set to a terminal according to the lesion corpus set;

Receiving a first selection result returned by the terminal according to the first option information set, and searching for a corresponding injury severity corpus from the semantic network according to the first selection result, and according to the injury severity corpus set, Sending, by the terminal, a second option information set;

Receiving a second selection result returned by the terminal according to the second option information set, and obtaining the second selection result from a preset matching data set according to the anatomical part information, the first selection result, and the second selection result Target matching data for the injured person; and

Acquiring preset claim data corresponding to the target matching data, obtaining target decision data according to the preset claim data, and sending the target decision data to the terminal.
The storage medium according to claim 15, wherein when the computer-readable instructions are executed by the processor, the following steps are further performed:

Receiving an injury picture of the injured person to be claimed sent by the terminal; and

The injury picture is input into a trained convolutional neural network to obtain information about the anatomical part corresponding to the injury picture.
The storage medium according to claim 15, wherein when the computer-readable instructions are executed by the processor, the following steps are further performed:

Acquiring a semantic tree of a preset dimension, the preset dimension including at least anatomy, lesions, and severity of injuries;

Calculate the co-occurrence frequency between the nodes corresponding to the semantic tree of each dimension and the nodes corresponding to the semantic tree of other dimensions; and

An association relationship is established between the two nodes whose co-occurrence frequency is greater than a preset threshold to generate a semantic network.
The storage medium according to claim 15, wherein when the computer-readable instructions are executed by the processor, the following steps are further performed:

Obtaining the weights corresponding to the anatomical site information, the first selection result, and the second selection result respectively;

Calculating the degree of matching of the anatomical site information, the first selection result, and the second selection result with each matching data separately; and

Calculate a matching score corresponding to each matching data according to the weight and the matching degree, and obtain the matching data with the largest matching score as the target matching data.
The storage medium according to claim 15, wherein when the computer-readable instructions are executed by the processor, the following steps are further performed:

For each lesion corpus in the lesion corpus, searching for corresponding description information from the description information set; and

A first option information set is obtained according to the description information corresponding to each lesion corpus.
The storage medium according to any one of claims 15 to 19, wherein when the computer-readable instructions are executed by the processor, the following steps are further performed:

When the number of the preset claims data is a preset amount, obtaining tag information corresponding to each piece of the preset claims data;

Obtaining personal information corresponding to the user identification; and

Obtain target decision data based on the tag information and the personal information.