CN113554365A - Diversified credit evaluation method for medical institution and related equipment - Google Patents
Diversified credit evaluation method for medical institution and related equipment Download PDFInfo
- Publication number
- CN113554365A CN113554365A CN202111111912.2A CN202111111912A CN113554365A CN 113554365 A CN113554365 A CN 113554365A CN 202111111912 A CN202111111912 A CN 202111111912A CN 113554365 A CN113554365 A CN 113554365A
- Authority
- CN
- China
- Prior art keywords
- information
- credit
- party
- data
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a diversified credit evaluation method and related equipment for medical institutions, which are realized by an open information server, an internal information server, a third-party information server and a credit evaluation server; the method comprises the following steps: the public information server, the internal information server and the third-party information server respectively acquire public credit information, internal credit information and third-party credit information of a target medical institution; the credit evaluation server respectively acquires the public credit information, the internal credit information and the third-party credit information from the public information server, the internal information server and the third-party information server, and inputs the public credit information, the internal credit information and the third-party credit information into a medical institution diversified credit evaluation model which is constructed in the credit evaluation server in advance to obtain a credit evaluation result of the target medical institution. The invention can evaluate the credit of the medical institution efficiently and accurately.
Description
Technical Field
The invention relates to the technical field of machine learning, in particular to a medical institution diversified credit evaluation method and related equipment.
Background
With the advent of the big data age, in the related art, when credit of a medical institution is evaluated, the evaluation result is generally obtained by the big data technology. Specifically, a large data multidimensional analysis technology is generally adopted, and multidimensional analysis is performed on credit information of the medical institution in a data warehouse construction mode to obtain a credit evaluation result of the medical institution.
However, when the evaluation is performed by the big data multidimensional analysis technology, the big data multidimensional analysis technology has a high requirement on the uniformity of the data (only normalized data can be analyzed), while the data for credit evaluation of the medical institution has different data types, such as data in a text form and data in an image form, and obviously, the big data multidimensional analysis technology cannot meet the requirement on the credit evaluation of the medical institution.
Disclosure of Invention
In view of the above, the present invention provides a diversified credit evaluation method for medical institutions and related devices.
In view of the above, the present invention provides a medical institution diversified credit evaluation method, which is implemented by a medical institution diversified credit evaluation system, wherein the medical institution diversified credit evaluation system includes: the system comprises a public information server, an internal information server, a third-party information server and a credit evaluation server; the medical institution diversified credit evaluation method comprises the following steps:
the public information server collects public credit information of a target medical institution;
the internal information server collects internal credit information of the target medical institution;
the third-party information server collects third-party credit information of the target medical institution;
the credit evaluation server respectively acquires the public credit information, the internal credit information and the third-party credit information from the public information server, the internal information server and the third-party information server;
and the credit evaluation server inputs the public credit information, the internal credit information and the third-party credit information into a medical institution diversified credit evaluation model which is constructed in the credit evaluation server in advance, so as to obtain a credit evaluation result of the target medical institution.
Based on the same inventive concept, the invention provides a diversified credit evaluation system for medical institutions, which comprises: the system comprises a public information server, an internal information server, a third-party information server and a credit evaluation server;
the public information server is configured to collect public credit information of a target medical institution;
the internal information server is configured to collect internal credit information of the target medical institution;
the third party information server is configured to collect third party credit information for the targeted medical facility;
the credit evaluation server is configured to acquire the public credit information, the internal credit information and the third party credit information from the public information server, the internal information server and the third party information server, respectively; inputting the public credit information, the internal credit information and the third-party credit information into a medical institution diversified credit evaluation model which is constructed in the credit evaluation server in advance, and obtaining a credit evaluation result of the target medical institution.
Based on the same inventive concept, the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, which when executing the program implements the method as described above.
From the above, the diversified credit evaluation method and the related equipment for the medical institution provided by the invention are realized by the public information server, the internal information server, the third-party information server and the credit evaluation server; the method comprises the following steps: the public information server, the internal information server and the third-party information server respectively acquire public credit information, internal credit information and third-party credit information of a target medical institution; the credit evaluation server respectively acquires the public credit information, the internal credit information and the third-party credit information from the public information server, the internal information server and the third-party information server, and inputs the public credit information, the internal credit information and the third-party credit information into a medical institution diversified credit evaluation model which is constructed in the credit evaluation server in advance to obtain a credit evaluation result of the target medical institution. The invention can evaluate the credit of the medical institution efficiently and accurately.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the related art, the drawings required to be used in the description of the embodiments or the related art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a diversified credit evaluation method for a medical institution according to an embodiment of the invention;
FIG. 2 is a flowchart illustrating a third-party credit preprocessing method according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a method for calculating information value of alternative indicators according to an embodiment of the present invention;
fig. 4 is a schematic flow chart of a data set partitioning method according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a scenario of a diversified credit evaluation model of a medical institution according to an embodiment of the invention;
FIG. 6 is a schematic structural diagram of a diversified credit evaluation device of a medical institution according to an embodiment of the invention;
fig. 7 is a schematic diagram of a more specific hardware structure of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to specific embodiments and the accompanying drawings.
It should be noted that technical terms or scientific terms used in the embodiments of the present invention should have the ordinary meanings as understood by those having ordinary skill in the art to which the present invention belongs, unless otherwise defined. The use of "first," "second," and similar language in the embodiments of the present invention does not denote any order, quantity, or importance, but rather the terms "first," "second," and similar language are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
As described in the background section, the large data multidimensional analysis technique employed in the related art cannot satisfy the requirement for credit evaluation of medical institutions. Specifically, credit information of medical institutions has the characteristic of various forms and has different data types, such as data in text form and data in image form, while the big data multidimensional technology can only analyze normalized data, that is, the requirement on the uniformity of the data is high, the credit information of the medical institutions in various forms is difficult to process, and the requirement on credit evaluation of the medical institutions cannot be met.
In view of the above, the present invention provides a diversified credit evaluation method for medical institutions and related devices.
Referring to fig. 1, a schematic flow chart of a diversified credit evaluation method for a medical institution according to an embodiment of the invention is shown. The medical institution diversified credit evaluation method is realized by a medical institution diversified credit evaluation system, wherein the medical institution diversified credit evaluation system comprises: the system comprises a public information server, an internal information server, a third-party information server and a credit evaluation server; the medical institution diversified credit evaluation method comprises the following steps:
and S110, the public information server collects the public credit information of the target medical institution.
The public credit information of the target medical institution refers to the public searchable credit information of the target medical institution. The public credit information is generally filed and issued by an information platform which is authenticated by authorities.
In some embodiments, the public credit information includes basic information, positive information, loss of credit information, and other public credit information.
As one example, the basic information contains basic cases of registration of the target medical institution, such as certification approval information, administrative approval information, and qualification information; also contains the basic situation of legal representatives, directors, supervisors and other major business managers of the target medical institution, such as identification information and occupational information; also included are basic situations of the medical staff of the target medical institution, such as practice qualification information, health professional technical qualification information.
As an example, the positive information includes information that the target medical institution is exposed, rewarded, and announced; information that the target medical institution is involved in voluntary services and charitable donation activities; the target medical institution participates in information of medical diagnosis, poverty relief, oral support, emergency rescue and disaster relief and health emergency activities; information on social public welfare activities of the target medical institution participating in the blood donation without compensation and the hematopoietic stem cells donated without compensation; and, the target medical institution is incorporated into the information of the credit-conserving joint incentives within the credit information sharing platform.
As one example, the information on loss of credit includes information that the target medical institution violates a credit commitment system; obtaining information of administrative permission, administrative confirmation, administrative payment and administrative reward by illegal means such as deception and bribery; administrative reexamination, administrative litigation or administrative reexamination and administrative litigation which are made by the health and health administrative department and are not lifted within the legal time limit, or the administrative penalty information which is originally determined is finally maintained through the administrative reexamination and the administrative litigation, except that the information is made by a simple program; information punished by market supervision and management departments due to illegal release of medical advertisements or false propaganda; information punished by market supervision and management departments due to non-standard charging and random charging; information checked and located by medical security departments due to fraudulent cheating and insurance behaviors; the crime forming information is judged and determined by the effective judgment of the people's court; information for medical institution adverse practice behavior scoring; counterfeiting, changing, buying and selling, renting, lending information of various health professional technical qualification certificates and practice certificates; through verification, in the production execution (operation) activity, the information of adulteration, filling in order, illegally adding and falsifying is doped; providing false materials, hiding facts or cheating information in supervision, title assessment, scientific research academy and examination; information of medical quality, medical safety or other safety accidents causing serious adverse consequences or major social influences; in the process of handling the emergency, the dispatch of a health administrative department is not obeyed; when an emergency occurs, effective measures are not taken in time according to related laws, regulations and regulations, or information which causes serious adverse effects is concealed, reported slowly, reported falsely and reported illegally; information that is enforced by law without fulfilling administrative decisions or does not fulfill human court decisions, sanctions and the like; refusing, hindering or resisting the information of supervising law enforcement of related departments with violence threat; refusing the information of the administrative penalty decision if the information is not qualified; the illegal behavior is regulated and corrected in time limit, and the information is not corrected after overdue; the rural order directionally and freely cultivates the information which is not specified by the directional employment agreement of medical students; the inpatients are trained on trainees in a standardized way, and the information of unproofed self is provided when the training tasks are not completed; information that the individual is not fulfilling the agreement with the work unit but is left unattended; the medical and health personnel are bribed or violate 'Jiuqian' regulation of medical and health wind construction, and the medical and health administrative department and the health administrative department are concerned about the responsibility or the transfer judicial authority is concerned about the information of criminal responsibility; information of loss of credit joint punishment in the credit information sharing platform is brought into; information on patients is solicited by adopting unfair means such as hiring 'doctor Tuo' and the like.
In some embodiments, the public credit information is represented in the form of both categorical data and numerical data.
The data of the category type is qualitative data, and can be represented in the form of binary data, that is, the value of the data is 1 or 0, where 1 represents hit and 0 represents miss. For example, whether the target medical institution has qualification information, the data of such information usually only has two cases of yes (namely hit) and no (miss), and meanwhile, since the public credit information is generally filed and issued by an information platform which is authorized by authority, the public credit information is more accurate and precise, the content of the part of the credit information can still be accurately expressed even through the qualitative data. The numerical data is quantitative data, such as information of participation of a target medical institution in volunteering services and charitable donation activities, the data of the information cannot be accurately expressed only by judging whether the information is available or not, and meanwhile, since public credit information is generally filed and issued by an information platform which is authorized by authority, the public credit information is accurate and precise, the content of the part of credit information is expressed by adopting the quantitative data, the accuracy of the data can not be lost, and meanwhile, the characteristic of better learning of the credit information by a machine learning algorithm can be realized.
And S120, the internal information server collects the internal credit information of the target medical institution.
The internal credit information of the target medical institution refers to the credit information which is not disclosed, but can be self-checked by the target medical institution.
The internal credit information is used as a supplement of public credit information, and provides undisclosed credit information in the public credit information and credit information with insufficient detail in the public credit information, wherein the undisclosed credit information in the public credit information, such as the information of the target medical institution for showing and punishing the internal medical and health staff; the public credit information includes original image information of credit information with insufficient detail, such as "doctor's certificate of authority", "nurse's certificate of authority", and "health professional qualification certificate".
In some embodiments, the internal credit information is represented by numerical data and image data.
Since the internal credit information is used as a supplement to the public credit information, the public credit information which is not disclosed in the public credit information and the public credit information which is not detailed enough are provided, the public credit information generally relates to the credit information with some specific details, and meanwhile, since the internal self-check is used, the accuracy of the information is questioned, the adoption of the category type data is too violent, and the numerical type data is adopted. The internal credit information provides image information, for example, original image information of "doctor's certificate of practice", "nurse's certificate of practice", and "health professional technical qualification certificate".
S130, the third-party information server collects the third-party credit information of the target medical institution.
The third party credit information of the target medical institution refers to the credit information of the target medical institution fed back by the third party.
The third party credit information supplements the public credit information and the internal credit information, and provides feedback supplementation of the credit information of the third party institution and the individual to the target medical institution.
In some embodiments, third party credit information employs categorical data. The third party credit information originates from a third party organization or an individual, the accuracy of the information is in doubt, and then whether the adopted type data is too hard or not is judged to be negative, because the data volume of the third party credit information is extremely large, the influence of the characteristics of single data on final evaluation is weakened, meanwhile, if the numerical data is adopted, the burden of a credit evaluation server on processing the third party credit information is undoubtedly increased, because the data volume of the third party credit information is extremely large, and therefore, in the invention, the third party credit information adopts the type data.
In some possible embodiments, the third party credit information is obtained by crawling through a web crawler technology, and since the third party credit information comes from a plurality of different third parties, a plurality of different data correspond to one alternative index. The data in the credit information of the third party is in the form of variables and values thereof, one variable corresponds to a plurality of values, and different values come from different third parties and describe the variable. The alternative index refers to a variable in the credit information of the third party.
Moreover, because the data volume of the third-party credit information is huge and has no obvious regularity, the invention also provides a technical means for preprocessing the third-party credit information, and filters out partial alternative indexes in the third-party credit information and data corresponding to the alternative indexes so as to further reduce the calculation resources required by the subsequent credit evaluation server for processing the third-party credit information.
In some embodiments, after the third-party information server collects the credit information of the third party of the target medical institution, the method further comprises:
and the third-party information server preprocesses the third-party credit information so as to reduce the computing resources required by the credit evaluation server for processing the third-party credit information.
The third-party credit information comprises a plurality of alternative indexes, wherein each alternative index corresponds to a plurality of data.
Referring to fig. 2, a flowchart of a third-party credit information preprocessing method according to an embodiment of the present invention is shown.
In some embodiments, the third party information server pre-processes the third party credit information, including:
s210, the third-party information server calculates the information value of each alternative index according to the data corresponding to the alternative index.
S220, the third-party information server filters the alternative indexes with the information value lower than the information value threshold value and the data corresponding to the alternative indexes to obtain the preprocessed third-party credit information.
Fig. 3 is a schematic flow chart of a method for calculating an information value of an alternative index according to an embodiment of the present invention.
The third-party information server calculates the information value of each alternative index according to the data corresponding to the alternative index, and the method comprises the following steps:
and S310, dividing the data corresponding to the alternative indexes into a plurality of data sets by the third-party information server.
S320, the third-party information server calculates the evidence weight of each data set.
The calculation formula is as follows:
(ii) a Wherein, WOEiIs the evidence weight, P, of the data set iBiIs the ratio of the number of hit data in the data set i to the number of hit data in the data corresponding to the candidate index, PGiThe ratio of the number of the missed data in the data set i to the number of the missed data in the data corresponding to the alternative indexes is obtained;
s330, the third-party information server calculates the information value of each data set according to the evidence weight of the data set.
The calculation formula is as follows:
(ii) a Wherein IViIs the information value of data set i;
and S340, calculating the value information of the alternative index by the third-party information server according to the information values of all the data sets.
The calculation formula is as follows:
(ii) a Where IV is the information value of the candidate index and n is the number of data sets.
Fig. 4 is a schematic flow chart of a data set partitioning method according to an embodiment of the present invention.
The third-party information server divides the data corresponding to the candidate index into a plurality of data sets, and the data sets comprise:
and S410, the third-party information server divides the data corresponding to the alternative indexes into a plurality of alternative data sets.
And S420, further determining whether the candidate data set simultaneously includes the hit data and the miss data, and for any one of the candidate data sets, in response to determining that the candidate data set does not simultaneously include the hit data and the miss data, the third-party information server merges the candidate data set with any one of the neighboring candidate data sets until the data set including the hit data and the miss data simultaneously is generated.
In some embodiments, optionally, the information value threshold is 0.01. That is, the index prediction ability of the IV value of 0.01 or less is considered to be low and can be discarded, and this part of data does not have the meaning of machine learning algorithm learning.
S140, the credit evaluation server obtains the public credit information, the internal credit information, and the third party credit information from the public information server, the internal information server, and the third party information server, respectively.
As described above, different credit information sources are greatly different, and at the same time, different credit information acquisition authorities are different, so the present invention provides an independent server to perform preliminary collection and preprocessing, and then the credit evaluation server acquires the public credit information, the internal credit information, and the third-party credit information from the public information server, the internal information server, and the third-party information server, respectively, so as to process the credit information together, and in this case, the privacy of other information in the public information server, the internal information server, and the third-party information server is also protected.
S150, the credit evaluation server inputs the public credit information, the internal credit information and the third-party credit information into a medical institution diversified credit evaluation model which is pre-constructed in the credit evaluation server to obtain a credit evaluation result of the target medical institution.
Wherein the public credit information, the internal credit information and the third party credit information respectively comprise category type data, numerical type data and image type data;
the medical institution diversified credit evaluation model comprises a multilayer perceptron, a convolutional neural network and a cyclic neural network;
referring to fig. 5, a scene diagram of a diversified credit evaluation model of a medical institution according to an embodiment of the invention is provided.
In some embodiments, the credit evaluation server inputs the public credit information, the internal credit information and the third-party credit information into a medical institution diversified credit evaluation model pre-constructed in the credit evaluation server to obtain a credit evaluation result of the target medical institution, including:
inputting the category type data and the numerical data into the multilayer perceptron in the medical institution diversified credit evaluation model to obtain the output of the multilayer perceptron;
inputting the image type data into the convolutional neural network in the medical institution diversified credit evaluation model to obtain the output of the convolutional neural network;
and connecting the output of the multilayer perceptron and the output of the convolutional neural network, and inputting the output into the recurrent neural network in the medical institution diversified credit evaluation model to obtain the output of the recurrent neural network as the credit evaluation result of the target medical institution.
The diversified credit evaluation model of the medical institution comprises two different input branches, namely a multilayer perceptron and a convolutional neural network, wherein the two branches operate independently before connection, and an output is generated through the convolutional neural network after connection. The multilayer perceptron is used for processing numerical value input, and the convolution neural network is used for processing image input.
Referring to fig. 5, the diversified credit evaluation model of the medical institution includes a multilayer perceptron, a convolutional neural network and a recurrent neural network.
The first input vector is constructed from the categorical data and the numerical data in the public credit information, the internal credit information, and the third party credit information.
A second input vector is constructed from the image-type data in the internal credit information.
As an example:
the first input vector is a feature vector describing features characterizing the public credit information, internal credit information and third party credit information of the targeted medical institution.
The second input vector is an image, and the image is optionally composed of a plurality of images, for example, composed of original images of "doctor's certificate of practice", "nurse's certificate of practice", and "health professional qualification certificate" of the target medical institution. Wherein the stitching order of the plurality of images is consistent for different medical institutions.
The first input vector is input into an input layer of a multi-layer perceptron.
The multi-layer perceptron compounds a plurality of hidden layers to process the first input vector. The parameters and number of the hidden layers can be adaptively set according to needs, which is not limited by the present disclosure. The neurons of the hidden layer are functional neurons with activation functions, each layer of neurons is fully interconnected with the next layer of neurons, and no connection of the same layer exists between the neurons and no connection of cross-layers exists between the neurons.
As an example, the multi-layer perceptron includes an input layer and three hidden layers. Inputting a 128-dimensional first input vector into an input layer, outputting a 64-dimensional credit information characteristic vector through a first hidden layer, outputting a 32-dimensional credit information characteristic vector through a second hidden layer, and outputting a 4-dimensional credit information characteristic vector through a third hidden layer.
Through a plurality of hidden layers, the multi-layer perceptron maps the first input vector into a 4-dimensional credit information feature vector as the output of the multi-layer perceptron.
The second input vector is input into an input layer of the convolutional neural network.
The convolutional neural network compounds the plurality of convolutional layers and the plurality of sampling layers to process the second input vector. The parameters and the number of convolutional layers and sampling layers can be adaptively set as required, and the convolutional layers and the sampling layers are briefly described by taking one convolutional layer and one sampling layer in a convolutional neural network as an example as follows:
for example, the size of the image of the input convolution layer is 32 × 32, the size of the convolution kernel is 5 × 5, the type of the convolution kernel is 6, the number of neurons is 4707, the size of the output feature map is 28 × 28, and the number of output feature maps is 6. I.e. 6 convolution kernels of 5 x 5, 6 signatures with a size of 28 x 28 were obtained.
The size of the image of the input sampling layer was (28 × 28) × 6 (6 feature maps with a size of 28 × 28 obtained by the above convolution layer), the size of the convolution kernel was 2 × 2, the type of convolution kernel was 6, the number of neurons was 1176, the size of the output downsampled map was 14, and the number of output downsampled maps was 6.
As an example, a convolutional neural network includes an input layer, three convolutional layers, two sampling layers, and a fully-connected layer.
The convolutional neural network maps the second input vector into a 4-dimensional credit information feature vector through a plurality of convolutional layers, a plurality of sampling layers and a full connection layer, and the credit information feature vector is used as the output of the convolutional neural network.
And connecting the output of the multilayer perceptron and the output of the convolutional neural network through linear combination to obtain 8-dimensional credit information characteristic vectors, and inputting the 8-dimensional credit information characteristic vectors into the recurrent neural network.
The recurrent neural network comprises an output layer and a plurality of hidden layers, the number of the hidden layers can be one or more than one, and the specific number can be set according to the requirement.
As one example, two hidden layers are included in the recurrent neural network.
The hidden layer comprises a plurality of neurons. For each neuron, the input of the neuron is the weighted sum of the output of each neuron of the previous hidden layer, and the input is output after an activation function; the activation function may select sigmoid, tanh, ReLU, etc., which is exemplified in this example. After passing through the first hidden layer, the output credit information feature vector is 2-dimensional; and after passing through a second hidden layer, the output credit information feature vector is 1-dimensional.
The activation function of the output layer may select Softmax, for example, the output layer obtains a vector (X), where X represents the credit rating of the target medical institution, that is, the 1-dimensional credit information feature vector is passed through the activation function to obtain the credit rating of the target medical institution as the credit evaluation result.
In some embodiments, the credit rating of the target medical institution may be output, and at the same time, the index having a large influence on the credit rating may be output, and a suggestion for improving the credit rating may be further generated according to the indexes and pushed to the terminal device of the target medical institution.
In some embodiments, the medical institution diversified credit evaluation method further comprises:
constructing a sample set comprising a plurality of samples; wherein the sample comprises: sample data and tag data; the sample data comprises public credit information for training, internal credit information for training and third-party credit information for training; the label data comprises training credit evaluation results;
and constructing and training the medical institution diversified credit evaluation model according to the sample set through a preset machine learning algorithm.
Sources of training data include, but are not limited to, existing databases, data crawled from the internet, or data uploaded while the user is using the client. When the accuracy of the medical institution diversified credit evaluation model output reaches a certain requirement, the medical institution diversified credit evaluation system can provide the medical institution diversified credit evaluation service for the user based on the medical institution diversified credit evaluation model, and meanwhile, the medical institution diversified credit evaluation system can continuously optimize the medical institution diversified credit evaluation model based on newly added training data.
From the above, the diversified credit evaluation method and the related equipment for the medical institution provided by the invention are realized by the public information server, the internal information server, the third-party information server and the credit evaluation server; the method comprises the following steps: the public information server, the internal information server and the third-party information server respectively acquire public credit information, internal credit information and third-party credit information of a target medical institution; the credit evaluation server respectively acquires the public credit information, the internal credit information and the third-party credit information from the public information server, the internal information server and the third-party information server, and inputs the public credit information, the internal credit information and the third-party credit information into a medical institution diversified credit evaluation model which is constructed in the credit evaluation server in advance to obtain a credit evaluation result of the target medical institution. The invention can evaluate the credit of the medical institution efficiently and accurately.
Aiming at the fact that credit information of a medical institution has a plurality of completely different information sources, the credit information processing system respectively collects corresponding credit information through a plurality of independent processors, guarantees privacy of the information sources, and meanwhile, is convenient for respectively preprocessing credit information data of different sources.
Aiming at the characteristics of large data volume and complexity of the credit information of the third party in the credit information of the medical institution, the method preprocesses the credit information of the third party, expresses the credit information of the third party through qualitative type data, filters out alternative indexes with information value lower than an information value threshold value and the data corresponding to the alternative indexes, and reduces the computing resources required by the credit evaluation server for processing the credit information of the third party.
Aiming at the characteristic that credit information forms of medical institutions are various, the invention utilizes a multilayer sensor to process classified data and numerical data, utilizes a convolutional neural network to process image data, connects the output of the multilayer sensor with the output of the convolutional neural network, and inputs the output of the convolutional neural network into the cyclic neural network to obtain the output of the cyclic neural network, and the output of the cyclic neural network is used as a credit evaluation result of a target medical institution. The evaluation result of the diversified credit evaluation model of the medical institution is more accurate.
It should be noted that the method of the embodiment of the present invention may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In the case of such a distributed scenario, one of the multiple devices may only perform one or more steps of the method according to the embodiment of the present invention, and the multiple devices interact with each other to complete the method.
It should be noted that the above describes some embodiments of the invention. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments described above and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Based on the same inventive concept, the invention also provides a diversified credit evaluation system for medical institutions, which corresponds to the method in any embodiment.
Referring to fig. 6, the medical institution diversification credit evaluation device includes: a public information server 610, an internal information server 620, a third party information server 630 and a credit rating server 640.
The public information server 610 is configured to collect public credit information for a targeted medical facility.
The internal information server 620 is configured to collect internal credit information of the targeted medical institution.
The third party information server 630 is configured to collect third party credit information for the targeted medical facility.
The credit evaluation server 640 is configured to obtain the public credit information, the internal credit information, and the third-party credit information from the public information server, the internal information server, and the third-party information server, respectively, and input the public credit information, the internal credit information, and the third-party credit information into a medical institution diversified credit evaluation model pre-constructed in the credit evaluation server, so as to obtain a credit evaluation result of the target medical institution.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, the functionality of the various modules may be implemented in the same one or more software and/or hardware implementations of the invention.
The device of the above embodiment is used for implementing the corresponding medical institution diversified credit evaluation method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, corresponding to any embodiment of the method, the invention further provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein when the processor executes the program, the diversified credit evaluation method for the medical institution according to any embodiment of the method is realized.
Fig. 7 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called to be executed by the processor 1010.
The input/output interface 1030 is used for connecting an input/output module to input and output information. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present apparatus and other apparatuses. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).
It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
The electronic device of the above embodiment is used to implement the corresponding medical institution diversified credit evaluation method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
It should be noted that the embodiments of the present invention can be further described in the following ways:
a medical institution diversified credit evaluation method is realized by a medical institution diversified credit evaluation system, wherein the medical institution diversified credit evaluation system comprises: the system comprises a public information server, an internal information server, a third-party information server and a credit evaluation server; the medical institution diversified credit evaluation method comprises the following steps:
the public information server collects public credit information of a target medical institution;
the internal information server collects internal credit information of the target medical institution;
the third-party information server collects third-party credit information of the target medical institution;
the credit evaluation server respectively acquires the public credit information, the internal credit information and the third-party credit information from the public information server, the internal information server and the third-party information server;
and the credit evaluation server inputs the public credit information, the internal credit information and the third-party credit information into a medical institution diversified credit evaluation model which is constructed in the credit evaluation server in advance, so as to obtain a credit evaluation result of the target medical institution.
Optionally, after the third-party information server collects the third-party credit information of the target medical institution, the method further includes:
and the third-party information server preprocesses the third-party credit information so as to reduce the computing resources required by the credit evaluation server for processing the third-party credit information.
Optionally, the third-party credit information includes a plurality of candidate indicators, and each candidate indicator corresponds to a plurality of data;
the third party information server preprocesses the third party credit information, and the third party credit information preprocessing comprises the following steps:
the third-party information server calculates the information value of each alternative index according to the data corresponding to the alternative index;
and the third-party information server filters the alternative indexes with the information value lower than the information value threshold value and the data corresponding to the alternative indexes to obtain the preprocessed third-party credit information.
Optionally, the calculating, by the third-party information server, for each candidate indicator, the information value of the candidate indicator according to the data corresponding to the candidate indicator includes:
the third-party information server divides the data corresponding to the alternative indexes into a plurality of data sets;
the third-party information server calculates the evidence weight of each data set, and the calculation formula is as follows:
(ii) a Wherein，WOEiIs the evidence weight, P, of the data set iBiIs the ratio of the number of hit data in the data set i to the number of hit data in the data corresponding to the candidate index, PGiThe ratio of the number of the missed data in the data set i to the number of the missed data in the data corresponding to the alternative indexes is obtained;
the third-party information server calculates the information value of each data set according to the evidence weight of the data set, and the calculation formula is as follows:
(ii) a Wherein IViIs the information value of data set i;
the third-party information server calculates the value information of the alternative index according to the information values of all the data sets, and the calculation formula is as follows:
(ii) a Where IV is the information value of the candidate index and n is the number of data sets.
Optionally, the dividing, by the third-party information server, the data corresponding to the candidate index into a plurality of data sets includes:
the third-party information server divides the data corresponding to the alternative indexes into a plurality of alternative data sets, and further determines whether the alternative data sets simultaneously contain hit data and miss data;
for any one of the candidate data sets, in response to determining that the candidate data set does not contain the hit data and the miss data at the same time, the third-party information server merges the candidate data set with any one of the neighboring candidate data sets until the data set containing the hit data and the miss data at the same time is generated.
Optionally, the public credit information, the internal credit information, and the third-party credit information respectively include category-type data, numerical-type data, and image-type data;
the medical institution diversified credit evaluation model comprises a multilayer perceptron, a convolutional neural network and a cyclic neural network;
the credit evaluation server inputs the public credit information, the internal credit information and the third-party credit information into a medical institution diversified credit evaluation model which is pre-constructed in the credit evaluation server to obtain a credit evaluation result of the target medical institution, and the method comprises the following steps:
inputting the category type data and the numerical data into the multilayer perceptron in the medical institution diversified credit evaluation model to obtain the output of the multilayer perceptron;
inputting the image type data into the convolutional neural network in the medical institution diversified credit evaluation model to obtain the output of the convolutional neural network;
and connecting the output of the multilayer perceptron and the output of the convolutional neural network, and inputting the output into the recurrent neural network in the medical institution diversified credit evaluation model to obtain the output of the recurrent neural network as the credit evaluation result of the target medical institution.
Optionally, the method further includes:
constructing a sample set comprising a plurality of samples; wherein the sample comprises: sample data and tag data; the sample data comprises public credit information for training, internal credit information for training and third-party credit information for training; the label data comprises training credit evaluation results;
and constructing and training the medical institution diversified credit evaluation model according to the sample set through a preset machine learning algorithm.
A healthcare facility diversification credit evaluation system comprising: the system comprises a public information server, an internal information server, a third-party information server and a credit evaluation server;
the public information server is configured to collect public credit information of a target medical institution;
the internal information server is configured to collect internal credit information of the target medical institution;
the third party information server is configured to collect third party credit information for the targeted medical facility;
the credit evaluation server is configured to acquire the public credit information, the internal credit information and the third party credit information from the public information server, the internal information server and the third party information server, respectively; inputting the public credit information, the internal credit information and the third-party credit information into a medical institution diversified credit evaluation model which is constructed in the credit evaluation server in advance, and obtaining a credit evaluation result of the target medical institution.
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method as described above when executing the program.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to those examples; within the idea of the invention, also technical features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the invention as described above, which are not provided in detail for the sake of brevity.
In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures for simplicity of illustration and discussion, and so as not to obscure the embodiments of the invention. Furthermore, devices may be shown in block diagram form in order to avoid obscuring embodiments of the present invention, and also in view of the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the embodiments of the present invention are to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the invention, it should be apparent to one skilled in the art that embodiments of the invention can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.
The present embodiments are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements and the like that may be made without departing from the spirit and principles of the embodiments of the present invention are intended to be included within the scope of the invention.
Claims (9)
1. A medical institution diversified credit evaluation method is realized by a medical institution diversified credit evaluation system, wherein the medical institution diversified credit evaluation system comprises: the system comprises a public information server, an internal information server, a third-party information server and a credit evaluation server; the medical institution diversified credit evaluation method comprises the following steps:
the public information server collects public credit information of a target medical institution;
the internal information server collects internal credit information of the target medical institution;
the third-party information server collects third-party credit information of the target medical institution;
the credit evaluation server respectively acquires the public credit information, the internal credit information and the third-party credit information from the public information server, the internal information server and the third-party information server;
and the credit evaluation server inputs the public credit information, the internal credit information and the third-party credit information into a medical institution diversified credit evaluation model which is constructed in the credit evaluation server in advance, so as to obtain a credit evaluation result of the target medical institution.
2. The method of claim 1, wherein after the third party information server collects third party credit information for the targeted medical facility, further comprising:
and the third-party information server preprocesses the third-party credit information so as to reduce the computing resources required by the credit evaluation server for processing the third-party credit information.
3. The method according to claim 2, wherein the third party credit information comprises a plurality of alternative indexes, and each alternative index corresponds to a plurality of data;
the third party information server preprocesses the third party credit information, and the third party credit information preprocessing comprises the following steps:
the third-party information server calculates the information value of each alternative index according to the data corresponding to the alternative index;
and the third-party information server filters the alternative indexes with the information value lower than the information value threshold value and the data corresponding to the alternative indexes to obtain the preprocessed third-party credit information.
4. The method according to claim 3, wherein the third-party information server calculates, for each candidate index, an information value of the candidate index according to the data corresponding to the candidate index, and includes:
the third-party information server divides the data corresponding to the alternative indexes into a plurality of data sets;
the third-party information server calculates the evidence weight of each data set, and the calculation formula is as follows:
(ii) a Wherein, WOEiIs the evidence weight, P, of the data set iBiIs the ratio of the number of hit data in the data set i to the number of hit data in the data corresponding to the candidate index, PGiThe ratio of the number of the missed data in the data set i to the number of the missed data in the data corresponding to the alternative indexes is obtained;
the third-party information server calculates the information value of each data set according to the evidence weight of the data set, and the calculation formula is as follows:
(ii) a Wherein IViIs the information value of data set i;
the third-party information server calculates the value information of the alternative index according to the information values of all the data sets, and the calculation formula is as follows:
(ii) a Where IV is the information value of the candidate index and n is the number of data sets.
5. The method of claim 4, wherein the third-party information server divides the data corresponding to the candidate metrics into a plurality of data sets, including:
the third-party information server divides the data corresponding to the alternative indexes into a plurality of alternative data sets, and further determines whether the alternative data sets simultaneously contain hit data and miss data;
for any one of the candidate data sets, in response to determining that the candidate data set does not contain the hit data and the miss data at the same time, the third-party information server merges the candidate data set with any one of the neighboring candidate data sets until the data set containing the hit data and the miss data at the same time is generated.
6. The method of claim 1, wherein the public credit information, the internal credit information, and the third party credit information include category type data, numerical type data, and image type data, respectively;
the medical institution diversified credit evaluation model comprises a multilayer perceptron, a convolutional neural network and a cyclic neural network;
the credit evaluation server inputs the public credit information, the internal credit information and the third-party credit information into a medical institution diversified credit evaluation model which is pre-constructed in the credit evaluation server to obtain a credit evaluation result of the target medical institution, and the method comprises the following steps:
inputting the category type data and the numerical data into the multilayer perceptron in the medical institution diversified credit evaluation model to obtain the output of the multilayer perceptron;
inputting the image type data into the convolutional neural network in the medical institution diversified credit evaluation model to obtain the output of the convolutional neural network;
and connecting the output of the multilayer perceptron and the output of the convolutional neural network, and inputting the output into the recurrent neural network in the medical institution diversified credit evaluation model to obtain the output of the recurrent neural network as the credit evaluation result of the target medical institution.
7. The method of claim 1, further comprising:
constructing a sample set comprising a plurality of samples; wherein the sample comprises: sample data and tag data; the sample data comprises public credit information for training, internal credit information for training and third-party credit information for training; the label data comprises training credit evaluation results;
and constructing and training the medical institution diversified credit evaluation model according to the sample set through a preset machine learning algorithm.
8. A healthcare facility diversification credit evaluation system comprising: the system comprises a public information server, an internal information server, a third-party information server and a credit evaluation server;
the public information server is configured to collect public credit information of a target medical institution;
the internal information server is configured to collect internal credit information of the target medical institution;
the third party information server is configured to collect third party credit information for the targeted medical facility;
the credit evaluation server is configured to acquire the public credit information, the internal credit information and the third party credit information from the public information server, the internal information server and the third party information server, respectively; inputting the public credit information, the internal credit information and the third-party credit information into a medical institution diversified credit evaluation model which is constructed in the credit evaluation server in advance, and obtaining a credit evaluation result of the target medical institution.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111111912.2A CN113554365A (en) | 2021-09-23 | 2021-09-23 | Diversified credit evaluation method for medical institution and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111111912.2A CN113554365A (en) | 2021-09-23 | 2021-09-23 | Diversified credit evaluation method for medical institution and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113554365A true CN113554365A (en) | 2021-10-26 |
Family
ID=78106533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111111912.2A Pending CN113554365A (en) | 2021-09-23 | 2021-09-23 | Diversified credit evaluation method for medical institution and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113554365A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150006261A1 (en) * | 2013-06-28 | 2015-01-01 | Healthtap, Inc. | Systems and method for evaluating and selecting a healthcare professional |
| CN105787064A (en) * | 2016-03-01 | 2016-07-20 | 广州铭诚计算机科技有限公司 | Mining platform establishment method based on big data |
| CN109543117A (en) * | 2018-10-16 | 2019-03-29 | 平安万家医疗投资管理有限责任公司 | Service push method and terminal device based on intelligent recommendation |
| CN109767068A (en) * | 2018-12-13 | 2019-05-17 | 平安科技（深圳）有限公司 | A kind of medical institutions' evaluation method, evaluating apparatus and computer readable storage medium |
| CN109830274A (en) * | 2019-02-02 | 2019-05-31 | 四川爱华立康智能科技有限公司 | A kind of electronic prescription shared system and sharing method |
| CN110826913A (en) * | 2019-11-07 | 2020-02-21 | 南京远致数据技术有限公司 | Medical service institution credit evaluation method and evaluation system |
| CN110827968A (en) * | 2018-08-08 | 2020-02-21 | 北京绪水互联科技有限公司 | Medical equipment evaluation method and system based on big data, electronic device and server |
| CN111598709A (en) * | 2020-06-29 | 2020-08-28 | 腾讯科技（深圳）有限公司 | Medical insurance data processing system, method, device, equipment and storage medium |
-
2021
- 2021-09-23 CN CN202111111912.2A patent/CN113554365A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150006261A1 (en) * | 2013-06-28 | 2015-01-01 | Healthtap, Inc. | Systems and method for evaluating and selecting a healthcare professional |
| CN105787064A (en) * | 2016-03-01 | 2016-07-20 | 广州铭诚计算机科技有限公司 | Mining platform establishment method based on big data |
| CN110827968A (en) * | 2018-08-08 | 2020-02-21 | 北京绪水互联科技有限公司 | Medical equipment evaluation method and system based on big data, electronic device and server |
| CN109543117A (en) * | 2018-10-16 | 2019-03-29 | 平安万家医疗投资管理有限责任公司 | Service push method and terminal device based on intelligent recommendation |
| CN109767068A (en) * | 2018-12-13 | 2019-05-17 | 平安科技（深圳）有限公司 | A kind of medical institutions' evaluation method, evaluating apparatus and computer readable storage medium |
| CN109830274A (en) * | 2019-02-02 | 2019-05-31 | 四川爱华立康智能科技有限公司 | A kind of electronic prescription shared system and sharing method |
| CN110826913A (en) * | 2019-11-07 | 2020-02-21 | 南京远致数据技术有限公司 | Medical service institution credit evaluation method and evaluation system |
| CN111598709A (en) * | 2020-06-29 | 2020-08-28 | 腾讯科技（深圳）有限公司 | Medical insurance data processing system, method, device, equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 范士雄等: "基于多源数据和模型融合的超短期母线负荷预测方法", 《电网技术》 * |
| 钱宗渊: "个人信用自动化评估方法的研究和应用", 《中国优秀博硕士学位论文全文数据库（硕士） 信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Barocas et al. | Fairness and machine learning: Limitations and opportunities | |
| US11259718B1 (en) | Systems and methods for automated body mass index calculation to determine value | |
| US11586177B2 (en) | Robotic process selection and configuration | |
| Madon et al. | Promoting police legitimacy among disengaged minority groups: Does procedural justice matter more? | |
| US11982993B2 (en) | AI solution selection for an automated robotic process | |
| Pope | Minorities and the juvenile justice system | |
| AU2021216391A1 (en) | Artificial intelligence selection and configuration | |
| US10748217B1 (en) | Systems and methods for automated body mass index calculation | |
| Goldenfein | Algorithmic transparency and decision-making accountability: Thoughts for buying machine learning algorithms | |
| Schrepel | Computational antitrust: An introduction and research agenda | |
| US10558916B2 (en) | Simulation system and method for integrating client behavioral preferences within decision-based simulation scenarios | |
| Hagendorff | From privacy to anti-discrimination in times of machine learning | |
| Ganguly et al. | A review of the role of causality in developing trustworthy ai systems | |
| Holmes | Righteous shoot or racial injustice? What crowdsourced data can (not) tell us about police-caused homicide | |
| Pang et al. | Sheep face recognition and classification based on an improved MobilenetV2 neural network | |
| Montasari | The application of big data predictive analytics and surveillance technologies in the field of policing | |
| Lokanan | The determinants of investment fraud: A machine learning and artificial intelligence approach | |
| CN113554365A (en) | Diversified credit evaluation method for medical institution and related equipment | |
| Gabriele | User Awareness of Privacy Risks Related to the Collection of Fitness Tracker Data | |
| Ojo | The emergence of artificial intelligence in Africa and its impact on the enjoyment of human rights | |
| Kurylets et al. | Threat modeling in RPA-Based systems | |
| Madan et al. | Automatic Image Tagging Using Tensor and Gaussian Filter | |
| Dixon et al. | AI and Corporate Social Responsibility | |
| Elnagar | INQUIRIES IN INTELLIGENT INFORMATION SYSTEMS: NEW TRAJECTORIES AND PARADIGMS | |
| Emerick et al. | The policy implications of research on fingerprint examination tasks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |