CN111666495A - Case recommendation method, device, equipment and storage medium - Google Patents
Case recommendation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111666495A CN111666495A CN202010506263.5A CN202010506263A CN111666495A CN 111666495 A CN111666495 A CN 111666495A CN 202010506263 A CN202010506263 A CN 202010506263A CN 111666495 A CN111666495 A CN 111666495A
- Authority
- CN
- China
- Prior art keywords
- case
- semantic
- elements
- similarity
- historical
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012549 training Methods 0.000 claims description 73
- 238000012545 processing Methods 0.000 claims description 34
- 238000010801 machine learning Methods 0.000 claims description 19
- 230000015654 memory Effects 0.000 claims description 17
- 238000013135 deep learning Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The application discloses a case recommendation method, a case recommendation device, case recommendation equipment and a storage medium, and relates to the technical field of knowledge maps and deep learning. The specific implementation scheme is as follows: receiving a case recommendation request from terminal equipment, wherein the case recommendation request is used for requesting to acquire a recommended case of a first case; acquiring a plurality of semantic elements of a first case, wherein the semantic elements are elements for describing case constitution; acquiring a recommended case of the first case from the historical cases according to the similarity of the first case and the historical cases to each semantic element and the weight of each semantic element, wherein the weight of the semantic elements is related to the type of the first case; and sending the recommended case to the terminal equipment. The implementation scheme improves the accuracy of case recommendation.
Description
Technical Field
The embodiment of the application relates to a knowledge graph technology in a computer technology, in particular to a case recommendation method, a case recommendation device, case recommendation equipment and a storage medium.
Background
In the case processing process, similar cases have important significance for quick and correct case processing.
At present, when a user needs to acquire similar cases of a current case, a recommendation request can be sent to a server through terminal equipment. After receiving the recommendation request, the server acquires the similar case of the current case according to the recommendation request, and sends the similar case of the current case to the terminal device to complete the recommendation of the similar case. The server may obtain similar cases of the current case by matching case attributes, where the case attributes may be, for example, a place, time, and a case cause of the case occurrence, and the cases obtained by matching the case attributes may include a large number of cases irrelevant to the current case because the case attributes are relatively wide. The server can also acquire recommended cases of cases by matching the text content of the cases, and since the same words may appear in completely unrelated cases, the method also has the problem that a large number of cases unrelated to the current case may be included in the acquired cases. That is, the accuracy of the currently recommended similar cases is not high.
Disclosure of Invention
The embodiment of the application provides a case recommendation method, device, equipment and storage medium, and improves case recommendation accuracy.
According to a first aspect, there is provided a case recommendation method, comprising: receiving a case recommendation request from terminal equipment, wherein the case recommendation request is used for requesting to acquire a recommended case of a first case; acquiring a plurality of semantic elements of a first case, wherein the semantic elements are elements for describing case constitution; acquiring a recommended case of the first case from the historical cases according to the similarity of the first case and the historical cases to each semantic element and the weight of each semantic element, wherein the weight of the semantic element is related to the type of the first case; and sending the recommended case to the terminal equipment.
The semantic elements in the application are elements for describing case composition, and the case composition of similar cases is similar, so that cases similar to the first case are selected from the historical cases as recommended cases according to the semantic elements of the first case and the semantic elements of the historical cases, and the case recommending accuracy can be improved. Meanwhile, the case type is considered by the weight of each semantic element in the embodiment, so that the case recommendation accuracy is further improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is a diagram of a system architecture provided by an embodiment of the present application;
FIG. 2 is a flowchart of a case recommendation method provided in an embodiment of the present application;
FIG. 3 is a schematic diagram of a process for obtaining weights of semantic elements related to types of a first case according to an embodiment of the present application;
FIG. 4 is a schematic structural diagram of a case recommendation device according to an embodiment of the present application;
FIG. 5 is a block diagram of an electronic device of a case recommendation method according to an embodiment of the application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
For a better understanding of the present application, the elements referred to in the present application will be explained first.
1. The cases in this implementation may be law-related cases, such as labor dispute-related cases, marital family dispute-related cases, and so on.
2. The properties of a case may include, but are not limited to, the following: the location of the case occurrence, the time of the case occurrence, and the case course.
3. The case is composed of but not limited to the following parts: prosecution claims, case details, basic conclusions, involved laws and regulations, or statutes.
Fig. 1 is a system architecture diagram provided in an embodiment of the present application, and referring to fig. 1, the system architecture includes a terminal device and a server. When a user needs to acquire similar cases of a current case, a recommendation request can be sent to a server through terminal equipment. After receiving the recommendation request, the server acquires the similar cases of the case according to the recommendation request, and sends the similar cases of the case to the terminal device.
At present, a server may obtain similar cases of a current case by matching case attributes, and cases obtained by matching case attributes may include a large number of cases irrelevant to the current case because case attributes are relatively wide, for example, cases of various types may occur at the same location. The server can also acquire similar cases of cases by matching the text content of the cases, and since the same words may appear in completely unrelated cases, the method also has the problem that a large number of cases unrelated to the current case may be included in the acquired cases. The cases obtained by the server include a large number of cases irrelevant to the current case, and the cases recommended to the user include a large number of cases irrelevant to the current case, that is, the accuracy of recommending similar cases is not high.
In order to solve the above technical problems, the inventors found that if two cases are similar, the configurations of the cases are similar, and therefore, similar cases can be recommended by matching the configurations of the cases. However, cases often relate to one or more legal documents, and each legal document is recorded with a large amount of text information, so that it is a technical problem how to extract the constitution of the case from the legal document corresponding to the case. In order to solve the technical problem, the inventor finds that accurate similar cases can be recommended for cases by acquiring semantic elements for describing the case constitution and matching the semantic elements among the cases.
The case recommendation method according to the present application will be described in detail below with specific examples.
Fig. 2 is a flowchart of a case recommendation method provided in an embodiment of the present application, and referring to fig. 2, the method of the embodiment includes:
step S201, the terminal device sends a case recommendation request to the server, wherein the case recommendation request is used for requesting to acquire a recommended case of the first case.
The terminal device can display a case recommendation interface, a user inputs a case recommendation instruction through the case recommendation interface, the case recommendation instruction comprises description information of a first case, and the terminal device generates a case recommendation request according to the case recommendation instruction and sends the case recommendation request to the server. It is understood that the case recommendation request also includes the description information of the first case.
Description information for the first case: in the first manner, the description information of the first case may include legal documents of the case, including but not limited to complaints, answers, court trial records, and the like. In a second aspect, the description information of the first case includes a plurality of semantic elements of the first case, wherein the semantic elements are elements describing the configuration of the case. As described above, case constituents may include, but are not limited to, at least one of: original appeal, case details and basic conclusion. Thus, the plurality of semantic elements of the first case may include, but is not limited to, at least two of: the case detail semantic elements are used for describing original complaints and complaints, the case detail semantic elements are used for describing case details, and the basic conclusion semantic elements are used for describing basic conclusions. The plurality of semantic elements of the first case can be obtained by carrying out structural processing on the first case.
For a case recommendation interface displayed by the terminal equipment: in one mode, when a user logs in a server by using a terminal device to inquire similar cases, the server sends a data stream to the terminal device, so that a case recommendation interface is displayed on a display screen of the terminal device.
Step S202, the server acquires a plurality of semantic elements of the first case, wherein the semantic elements are elements for describing the case structure.
When the description information of the first case comprises legal documents of the case, the server acquires a plurality of semantic elements of the first case, including: the server acquires a plurality of semantic elements of the first case according to the legal document of the first case. For example, the server may obtain a plurality of semantic elements of the first case according to the legal document of the first case through the first machine learning model. The first machine learning model is obtained based on a plurality of second training samples, and each second training sample comprises legal documents of a second training case and a plurality of semantic elements included in the second training case. The first machine learning model may be a neural network model. According to the first machine learning model, the efficiency of obtaining the plurality of semantic elements of the first case is high.
When the description information of the first case comprises a plurality of semantic elements of the first case, the server acquires the plurality of semantic elements of the first case, and the method comprises the following steps: after receiving the case recommendation request, the server extracts a plurality of semantic elements of the first case included in the case request.
Step S203, the server acquires the recommended case of the first case from the historical case according to the similarity of the first case and the historical case for each semantic element and the weight of each semantic element, wherein the weight of each semantic element is related to the type of the first case.
Obtaining semantic elements of the history cases: the server can acquire each semantic element of the historical case according to the legal documents of the historical case through the first machine learning model; semantic elements of the history case input by the user can also be received.
For cases of different types, because the contribution of each semantic element that enables a case to be distinguished from other cases may not be the same, the weights of the semantic elements corresponding to the cases of different types may not be the same. The case types include, but are not limited to, the following: personality right dispute case, marriage family dispute case, inheritance dispute case, real estate registration dispute case, property right protection dispute case, ownership dispute case, and the like.
Illustratively, each semantic element includes: original appeal semantic elements, case detail semantic elements and basic conclusion semantic elements. For cases of marital family disputes, the weight of the original appeal semantic element is 0.4, the weight of the case detail semantic element is 0.4, and the weight of the basic conclusion semantic element is 0.2. For the personality-weight dispute case, the weight of the original-notice claiming semantic element is 0.3, the weight of the case detail semantic element is 0.4, and the weight of the basic conclusion semantic element is 0.3.
And step S204, the server sends the recommended case of the first case to the terminal equipment.
After acquiring the recommended case of the first case, the server can send the recommended case of the first case to the terminal device, and the terminal device displays the recommended case of the first case.
As described above, the semantic elements are elements describing case configurations, and case configurations of similar cases are similar, so that cases similar to the first case are selected from the historical cases as recommended cases according to the semantic elements of the first case and the semantic elements of the historical cases, and accuracy of case recommendation can be improved. Meanwhile, the case type is considered by the weight of each semantic element in the embodiment, so that the case recommendation accuracy is further improved.
The embodiment shown in fig. 2 is further described below using several specific embodiments.
It can be understood that, before the server obtains the recommended case of the first case from the historical cases, the method further includes: the server acquires the similarity of the first case and the historical case aiming at each semantic element. The following describes a specific implementation of the server acquiring the similarity between the first case and the historical case for each semantic element by using a specific embodiment.
First, semantic elements will be explained.
Each semantic element may include at least one semantic tag. Such as: the original appeal elements include: the semantic labels of the original complaint claim indemnity medical fee, the original complaint claim indemnity labor fee and the case detail elements comprise: the semantic labels of traffic accidents of the motor vehicles and pedestrians are reported to drive the motor vehicles, be driven after being drunk and be generated. The basic conclusion elements include: support medical fee appeal, support malwork fee appeal semantic tags.
Optionally, a semantic tag included in any one of the plurality of semantic elements is a semantic tag in a first preset semantic tag set. That is, for a certain case, the description mode of the semantic tag included in the first semantic element is defined in advance. The optional mode ensures the realization of the first realization mode for subsequently acquiring the similarity of the first case and the historical case aiming at the first semantic element, namely the acquired similarity of the first case and the historical case aiming at the first semantic element can be more accurate.
Illustratively, the first semantic element is an original appeal element, and the first preset semantic tag set includes: original complaints claim for medical fees, original complaints claim for misemployment fees, original complaints claim for profit margins, original complaints for property segments, original complaints for divorce, and the like. The first training case 1 is a case that the user a drives a car and collides the user B, and according to related legal documents of the case, the B claim a can be known to compensate medical fees and labor costs, and the original complaint claim elements of the first training case 1 include two semantic tags, namely original complaint claim medical fees and original complaint claim fee and labor costs, in the first preset semantic tag set.
Alternatively, for any first semantic element of the plurality of semantic elements, there is no first preset semantic tag set corresponding to the first semantic element, that is, for a certain case, the description mode of the semantic tag included in the first semantic element is not well defined in advance.
Next, a method of acquiring the similarity between the first case and the historical case with respect to the semantic elements will be described by taking as an example a method of acquiring the similarity between the first case and the historical case with respect to the first semantic elements.
The method comprises the following steps that a first semantic element of a first case comprises at least one first semantic tag, a first semantic element of a historical case comprises at least one second semantic tag, and a server acquires the similarity of the first case and the historical case aiming at the first semantic element, and comprises the following steps: the server obtains the similarity of the first case and the historical case aiming at the first semantic element according to at least one first semantic tag and at least one second semantic tag.
In a first implementation manner, the server obtains the similarity of the first semantic element between the first case and the historical case according to at least one first semantic tag and at least one second semantic tag, where the similarity includes the following a 1-a 4:
a1, the server determines the number of the first semantic tags as a first number;
a2, the server determines the number of the second semantic tags to be a second number;
a3, the server determines that a third number of the same semantic tags exist in the first number of first semantic tags and the second number of second semantic tags.
a4, the server acquires the similarity of the first case and the historical case aiming at the first semantic element according to the first number, the second number and the third number.
The server obtains the similarity of the first case and the historical cases aiming at the first semantic elements according to the first quantity, the second quantity and the third quantity, and comprises the following steps: the server acquires a first ratio of the third quantity to the first quantity; acquiring a second ratio of the third quantity to the second quantity; and determining the product of the first ratio and the second ratio as the similarity of the first case and the historical case for the first semantic element.
Illustratively, the first semantic element is a case detail element, the case detail element of the first case comprises 3 first semantic tags of the motor vehicle being reported to be driven, the motor vehicle being drunk to be driven and the traffic accident between the motor vehicle and the pedestrian, and the case detail element of the historical case comprises 2 second semantic tags of the motor vehicle being reported to be driven and the traffic accident between the motor vehicle and the pedestrian, namely, the first number is 3 and the second number is 2. There are 2 identical semantic tags in the 3 first semantic tags and the 2 second semantic tags, i.e. the third number is 2. Then the similarity of the first case and the historical case for the case detail semantic elements is equal to (2/3) × (2/2) ═ 2/3.
The first implementation manner is applicable to the semantic tags included in the first semantic element being semantic tags in the first preset semantic tag set. The similarity between the first case and the historical case acquired in the implementation mode is more accurate aiming at the first semantic element.
In a second implementation manner, the obtaining, by a server, a similarity of a first case and a historical case for a first semantic element according to at least one first semantic tag and at least one second semantic tag includes: the server obtains the similarity of the first case and the historical case aiming at the first semantic element according to the semantic similarity between at least one first semantic tag and at least one second semantic tag.
In one mode, a server obtains the similarity of a first case and a historical case for a first semantic element according to the semantic similarity between at least one first semantic tag and at least one second semantic tag, and the method comprises the following steps: for each first semantic label, the server acquires semantic similarity between the first semantic label and each second semantic label and determines the maximum semantic similarity; the server determines that the number of the first semantic tags is a first number, determines that the number of the second semantic tags is a second number, and obtains the similarity of the first case and the historical case for the first semantic elements according to the maximum semantic similarity, the first number and the second number. The method for obtaining the semantic similarity between the texts can be obtained by the current general method.
Optionally, the obtaining, by the server, the similarity of the first case and the historical case for the first semantic element according to the maximum semantic similarity, the first number, and the second number includes: and the server acquires a third ratio and determines that the product of the third ratio and the maximum semantic similarity is the similarity of the first case and the historical case for the first semantic element. The third ratio is a ratio of the first quantity to the second quantity when the first quantity is less than or equal to the second quantity, and the third ratio is a ratio of the second quantity to the first quantity when the first quantity is greater than the second quantity.
The second implementation manner is applicable to the case where there is no first preset semantic tag set corresponding to the first semantic element. The process of acquiring the similarity of the first case and the historical case aiming at the first semantic elements in the implementation mode is simpler than that of the first implementation mode.
The embodiment provides a method for acquiring the similarity of a first case and a historical case for a first semantic element.
It can be understood that, before obtaining the recommended case of the first case from the historical cases, the method further includes: acquiring the weight of each semantic element related to the first case type, wherein the type of each semantic element in the embodiment is the types of a plurality of semantic elements of the first case in the previous embodiment. The following describes a method for obtaining the weight of each semantic element related to the first case type by using a specific embodiment.
The weight of each semantic element related to the first case type can be obtained by training based on a plurality of first training samples, and the types of a plurality of first training cases corresponding to the plurality of first training samples are the same as the type of the first case; each first training sample comprises a plurality of semantic elements of a first training case and a law related to the first training case.
Optionally, the weight of each semantic element related to the first case type is stored in the server after the server in the embodiment shown in fig. 2 is trained based on a plurality of first training samples.
Optionally, the weight of each semantic element related to the first case type is sent to the server in the embodiment shown in fig. 2 after the other server is trained based on the plurality of first training samples.
Wherein training the weight of each semantic element related to the first case type based on a plurality of first training samples comprises c 1-c 3 as follows:
c1, acquiring a plurality of semantic elements of a plurality of first training cases and the law related to the first training cases to obtain a plurality of first training samples, wherein the types of the plurality of first training cases are the same as the type of the first case. The types of the semantic elements of the first training case are the types of the semantic elements of the first case in the previous embodiment.
In one embodiment, the plurality of semantic elements of the plurality of first training cases and the corresponding legal rules of the first training case may be obtained based on a second machine learning model trained in advance. In training the second machine learning model, the input may be a legal document to which the third training sample relates, and the output is expected to be a plurality of semantic elements and a related legal clause of the third training sample.
Alternatively, the semantic elements and the rules of the first training case may be input into the server in the embodiment shown in fig. 2 by the user, for example, the semantic elements and the rules of the first training case are input by the user through the terminal device, and the terminal device sends the semantic elements and the rules to the server in the embodiment shown in fig. 2.
Optionally, the semantic tags included in the law related to the case are semantic tags in a preset law semantic tag set. That is, for a case, the description mode of the semantic tags included in the law is specified in advance.
Optionally, there is no preset french semantic tag set corresponding to the french, that is, for a certain case, the description mode of the semantic tags included in the french is not well defined in advance.
And c2, acquiring the preselected weight of each semantic element.
The method for pre-selecting the weight of each semantic element can be randomly selected or preset weight.
And c3, adjusting the preselected weight of each semantic element based on a plurality of first training samples by adopting a machine learning algorithm to obtain the weight of each semantic element related to the type of the first case.
In one embodiment, in the training process, the plurality of semantic elements and the preselection weight of the first training sample are used as input of the machine learning model, the law related to the first training sample is used as expected output of the machine learning model, the preselection weight is adjusted according to an error between the actual output and the expected output, and the preselection weight of each semantic element corresponding to a case where the error between the actual output and the expected output is within a preset range is determined as the weight of each semantic element related to the type of the first case. A schematic process diagram of training to obtain the weight of each semantic element related to the type of the first case may be shown in fig. 3.
The embodiment provides a method for acquiring the weight of each semantic element related to the type of the first case, and the accurate weight of each semantic element can be obtained by considering the type of the case.
Next, a specific implementation of the server acquiring the recommended case of the first case from the historical cases according to the similarity between the first case and the historical cases for each semantic element and the weight of each semantic element will be described with a specific embodiment.
The server acquires the recommended case of the first case from the historical cases according to the similarity of the first case and the historical cases to each semantic element and the weight of each semantic element, wherein the recommended case comprises the following d 1-d 2:
d1, the server calculates the similarity total score according to the similarity of the first case and the historical case aiming at each semantic element and the weight of each semantic element related to the type of the first case.
Illustratively, each semantic element includes: original appeal semantic elements, case detail semantic elements and basic conclusion semantic elements. The type of the first case is marital family dispute, the weight of the corresponding original appeal semantic element is 0.4, the weight of the case detail semantic element is 0.4, and the weight of the basic conclusion semantic element is 0.2. The similarity between the original appeal semantic element of the first case and the original appeal semantic element of the history case 1 is 3/4, the similarity between the case detail semantic element of the first case and the case detail semantic element of the history case 1 is 3/5, the similarity between the basic conclusion semantic element of the first case and the basic conclusion semantic element of the history case 1 is 1/2, and the total similarity score between the first case and the history case 1 is equal to: 3/4 × 0.4+3/5 × 0.4+1/2 × 0.2 ═ 16/25.
d2, the server acquires the recommended case of the first case from the historical cases based on the similarity total score.
After the total similarity score between each historical case and the first case is obtained, the total similarity score can be sorted from high to low, and the N historical cases with the top N in the sorting order are used as recommended cases of the first case. N is an integer greater than or equal to 1.
In the embodiment, a specific implementation that the server acquires the recommended case of the first case from the historical cases according to the similarity of the first case and the historical cases to each semantic element and the weight of each semantic element is given.
The method according to the present application is explained above, and the apparatus according to the present application is explained below using specific examples.
Fig. 4 is a schematic structural diagram of a case recommendation device provided in an embodiment of the present application, and as shown in fig. 4, the case recommendation device of the present embodiment may include: a transceiver module 41 and a processing module 42.
A transceiver module 41, configured to receive a case recommendation request from a terminal device, where the case recommendation request is used to request to acquire a recommended case of a first case;
a processing module 42, configured to obtain multiple semantic elements of a first case, where the semantic elements are elements describing a case structure;
the processing module 42 is further configured to obtain a recommended case of the first case from the historical cases according to the similarity between the first case and the historical cases for each semantic element and the weight of each semantic element, where the weight of the semantic element is related to the type of the first case;
the transceiver module 41 is further configured to send the recommended case to the terminal device.
In one embodiment, the weight of each semantic element is obtained based on a plurality of first training samples, and the types of a plurality of first training cases corresponding to the plurality of first training samples are the same as the type of the first case; each first training sample comprises the multiple types of semantic elements of one first training case and the law related to the first training case.
In one embodiment, before the processing module 42 obtains the recommended case for the first case from the historical cases, the processing module 42 is further configured to: obtaining the multi-type semantic elements of the plurality of first training cases of the type to obtain a plurality of first training samples; obtaining preselection weight of each semantic element; and adjusting the preselected weight based on the plurality of first training samples by adopting a machine learning algorithm to obtain the weight of each semantic element.
In one embodiment, the semantic elements of the first case include at least one first semantic tag, the semantic elements of the historical cases include at least one second semantic tag, and before processing module 42 retrieves the recommended case of the first case from the historical cases, processing module 42 is further configured to: and according to the at least one first semantic label and the at least one second semantic label, acquiring the similarity of the first case and the historical case aiming at the semantic elements.
In one embodiment, the processing module 42 is specifically configured to: determining the number of the first semantic tags to be a first number; determining the number of the second semantic tags to be a second number; determining that a third number of identical semantic tags exist in the first number of first semantic tags and the second number of second semantic tags; and according to the first quantity, the second quantity and the third quantity, acquiring the similarity of the first case and the historical case aiming at the semantic elements.
In one embodiment, the processing module 42 is specifically configured to: obtaining a first ratio of the third quantity to the first quantity; obtaining a second ratio of the third quantity to the second quantity; and determining the product of the first ratio and the second ratio as the similarity of the first case and the historical case for the semantic elements.
In one embodiment, the semantic tags included in the semantic element are semantic tags in a first preset semantic tag set.
In one embodiment, before the processing module 42 is configured to obtain the recommended case of the first case from the historical cases, the processing module 42 is further configured to: and obtaining the first similarity according to the semantic similarity between the at least one first semantic label and the at least one second semantic label.
In one embodiment, the case recommendation request includes description information of a first case; the processing module 42 is specifically configured to: acquiring a plurality of semantic elements of a first case according to the description information of the first case and a first machine learning model; wherein the first machine learning model is obtained based on a plurality of second training samples, each second training sample including description information of a second training case and the plurality of semantic elements included in the second training case.
In one embodiment, the processing module 42 is specifically configured to: calculating a total similarity score according to the similarity of the first case and the historical cases to each semantic element and the weight of each semantic element; and acquiring the recommended case of the first case from the historical cases based on the similarity total score.
In one embodiment, the plurality of semantic elements may include at least two of the following: original appeal elements, case detail elements and case basic conclusion elements.
The apparatus of this embodiment may be configured to implement the technical solutions of the above method embodiments, and the implementation principles and technical effects are similar, which are not described herein again.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
Fig. 5 is a block diagram of an electronic device according to the case recommendation method of the embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 5, the electronic apparatus includes: one or more processors 501, memory 502, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 5, one processor 501 is taken as an example.
The memory 502, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules (e.g., the transceiver module 401 and the processing module 402 shown in fig. 4) corresponding to the case recommendation method in the embodiments of the present application. The processor 501 executes various functional applications of the server and data processing by running non-transitory software programs, instructions, and modules stored in the memory 502, that is, implements the case recommendation method in the above method embodiment.
The memory 502 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the electronic device recommended by the case, and the like. Further, the memory 502 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 502 may optionally include memory located remotely from the processor 501, which may be connected to the case recommendation electronics over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the case recommendation method may further include: an input device 503 and an output device 504. The processor 501, the memory 502, the input device 503 and the output device 504 may be connected by a bus or other means, and fig. 5 illustrates the connection by a bus as an example.
The input device 503 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the case-recommended electronic apparatus, such as an input device such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, or the like. The output devices 504 may include a display device, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
According to the technical scheme of the embodiment of the application, the semantic elements are elements for describing case composition, the case composition of similar cases is similar, and cases similar to the first case are selected from the historical cases as recommended cases according to the semantic elements of the first case and the semantic elements of the historical cases, so that the case recommendation accuracy can be improved. Meanwhile, the case type is considered by the weight of each semantic element in the embodiment, so that the case recommendation accuracy is further improved.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (24)
1. A case recommendation method is characterized by comprising the following steps:
receiving a case recommendation request from terminal equipment, wherein the case recommendation request is used for requesting to acquire a recommended case of a first case;
acquiring a plurality of semantic elements of a first case, wherein the semantic elements are elements for describing case constitution;
acquiring a recommended case of the first case from the historical cases according to the similarity of the first case and the historical cases to each semantic element and the weight of each semantic element, wherein the weight of the semantic element is related to the type of the first case;
and sending the recommended case to the terminal equipment.
2. The method according to claim 1, wherein the weight of each semantic element is obtained based on a plurality of first training samples, and the types of a plurality of first training cases corresponding to the plurality of first training samples are all the same as the type of the first case;
each first training sample comprises the multiple types of semantic elements of one first training case and the law related to the first training case.
3. The method of claim 2, before obtaining the recommended case of the first case from the historical cases, further comprising:
obtaining the multi-type semantic elements of the plurality of first training cases of the type to obtain a plurality of first training samples;
obtaining preselection weight of each semantic element;
and adjusting the preselected weight based on the plurality of first training samples by adopting a machine learning algorithm to obtain the weight of each semantic element.
4. The method according to any one of claims 1 to 3, wherein the semantic elements of the first case comprise at least one first semantic tag, the semantic elements of the historical cases comprise at least one second semantic tag, and before obtaining the recommended case of the first case from the historical cases, the method further comprises:
and according to the at least one first semantic label and the at least one second semantic label, acquiring the similarity of the first case and the historical case aiming at the semantic elements.
5. The method according to claim 4, wherein the obtaining the similarity of the first case and the historical case with respect to the semantic elements according to the at least one first semantic tag and the at least one second semantic tag comprises:
determining the number of the first semantic tags to be a first number;
determining the number of the second semantic tags to be a second number;
determining that a third number of identical semantic tags exist in the first number of first semantic tags and the second number of second semantic tags;
and according to the first quantity, the second quantity and the third quantity, acquiring the similarity of the first case and the historical case aiming at the semantic elements.
6. The method according to claim 5, wherein the obtaining the similarity of the first case and the historical case with respect to the semantic elements according to the first number, the second number and the third number comprises:
obtaining a first ratio of the third quantity to the first quantity;
obtaining a second ratio of the third quantity to the second quantity;
and determining the product of the first ratio and the second ratio as the similarity of the first case and the historical case for the semantic elements.
7. The method according to claim 5, wherein the semantic tags included in the semantic elements are semantic tags in a first preset semantic tag set.
8. The method of claim 4, further comprising, prior to obtaining the recommended case for the first case from the historical cases:
and obtaining the first similarity according to the semantic similarity between the at least one first semantic label and the at least one second semantic label.
9. The method according to any one of claims 1 to 3, wherein the case recommendation request includes description information of the first case, and the obtaining of the plurality of semantic elements of the first case includes:
acquiring a plurality of semantic elements of the first case according to the description information of the first case and a first machine learning model;
wherein the first machine learning model is obtained based on a plurality of second training samples, each second training sample including description information of a second training case and the plurality of semantic elements included in the second training case.
10. The method according to any one of claims 1 to 3, wherein the obtaining of the recommended case of the first case from the historical cases according to the similarity of the first case and the historical cases for each semantic element and the weight of each semantic element comprises:
calculating a total similarity score according to the similarity of the first case and the historical cases to each semantic element and the weight of each semantic element;
and acquiring the recommended case of the first case from the historical cases based on the similarity total score.
11. The method of claim 1, wherein the plurality of semantic elements comprises at least two of the following: original appeal elements, case detail elements and case basic conclusion elements.
12. A case recommendation device, comprising:
the system comprises a receiving and sending module, a case recommending module and a case recommending module, wherein the receiving and sending module is used for receiving a case recommending request from terminal equipment, and the case recommending request is used for requesting to acquire a recommended case of a first case;
the system comprises a processing module, a processing module and a processing module, wherein the processing module is used for acquiring a plurality of semantic elements of a first case, and the semantic elements are elements for describing case constitution;
the processing module is further used for acquiring a recommended case of the first case from the historical cases according to the similarity of the first case and the historical cases to each semantic element and the weight of each semantic element, wherein the weight of the semantic element is related to the type of the first case;
and the transceiver module is also used for sending the recommended case to the terminal equipment.
13. The apparatus according to claim 12, wherein the weight of each semantic element is obtained based on a plurality of first training samples, and the types of a plurality of first training cases corresponding to the plurality of first training samples are all the same as the type of the first case;
each first training sample comprises the multiple types of semantic elements of one first training case and the law related to the first training case.
14. The apparatus of claim 13, wherein before the processing module obtains the recommended case for the first case from the historical cases, the processing module is further configured to:
obtaining the multi-type semantic elements of the plurality of first training cases of the type to obtain a plurality of first training samples;
obtaining preselection weight of each semantic element;
and adjusting the preselected weight based on the plurality of first training samples by adopting a machine learning algorithm to obtain the weight of each semantic element.
15. The apparatus according to any one of claims 12 to 14, wherein the semantic elements of the first case comprise at least one first semantic tag, the semantic elements of the historical cases comprise at least one second semantic tag, and before the processing module obtains the recommended case of the first case from the historical cases, the processing module is further configured to:
and according to the at least one first semantic label and the at least one second semantic label, acquiring the similarity of the first case and the historical case aiming at the semantic elements.
16. The apparatus of claim 15, wherein the processing module is specifically configured to:
determining the number of the first semantic tags to be a first number;
determining the number of the second semantic tags to be a second number;
determining that a third number of identical semantic tags exist in the first number of first semantic tags and the second number of second semantic tags;
and according to the first quantity, the second quantity and the third quantity, acquiring the similarity of the first case and the historical case aiming at the semantic elements.
17. The apparatus of claim 16, wherein the processing module is specifically configured to:
obtaining a first ratio of the third quantity to the first quantity;
obtaining a second ratio of the third quantity to the second quantity;
and determining the product of the first ratio and the second ratio as the similarity of the first case and the historical case for the semantic elements.
18. The apparatus according to claim 16, wherein the semantic tags included in the semantic element are semantic tags in a first preset semantic tag set.
19. The apparatus of claim 15, wherein before the processing module obtains the recommended case for the first case from the historical cases, the processing module is further configured to:
and obtaining the first similarity according to the semantic similarity between the at least one first semantic label and the at least one second semantic label.
20. The apparatus according to any one of claims 12 to 14, wherein the case recommendation request includes description information of the first case, and the processing module is specifically configured to:
acquiring a plurality of semantic elements of a first case according to the description information of the first case and a first machine learning model;
wherein the first machine learning model is obtained based on a plurality of second training samples, each second training sample including description information of a second training case and the plurality of semantic elements included in the second training case.
21. The device according to any one of claims 12 to 14, wherein the processing module is specifically configured to:
calculating a total similarity score according to the similarity of the first case and the historical cases to each semantic element and the weight of each semantic element;
and acquiring the recommended case of the first case from the historical cases based on the similarity total score.
22. The apparatus of claim 12, wherein the plurality of semantic elements comprises at least two of: original appeal elements, case detail elements and case basic conclusion elements.
23. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.
24. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-11.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010506263.5A CN111666495B (en) | 2020-06-05 | 2020-06-05 | Case recommending method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010506263.5A CN111666495B (en) | 2020-06-05 | 2020-06-05 | Case recommending method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111666495A true CN111666495A (en) | 2020-09-15 |
CN111666495B CN111666495B (en) | 2023-08-11 |
Family
ID=72386432
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010506263.5A Active CN111666495B (en) | 2020-06-05 | 2020-06-05 | Case recommending method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111666495B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112015774A (en) * | 2020-09-25 | 2020-12-01 | 北京百度网讯科技有限公司 | Chart recommendation method and device, electronic equipment and storage medium |
CN112348714A (en) * | 2020-11-05 | 2021-02-09 | 科大讯飞股份有限公司 | Evidence chain construction method, electronic device and storage medium |
CN112925899A (en) * | 2021-02-09 | 2021-06-08 | 重庆中科云从科技有限公司 | Ranking model establishing method, case clue recommending device and medium |
CN113947290A (en) * | 2021-09-26 | 2022-01-18 | 海南电网有限责任公司 | Distribution network evaluation and review auxiliary method and system based on artificial intelligence |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160350377A1 (en) * | 2015-05-29 | 2016-12-01 | International Business Machines Corporation | Estimating the cost of data-mining services |
CN108280149A (en) * | 2018-01-04 | 2018-07-13 | 东南大学 | A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort |
CN109783640A (en) * | 2018-12-20 | 2019-05-21 | 广州恒巨信息科技有限公司 | One type case recommended method, system and device |
CN110020134A (en) * | 2017-11-09 | 2019-07-16 | 北京国双科技有限公司 | A kind of method for pushing, system, storage medium and the processor of knowledge services information |
WO2019171040A1 (en) * | 2018-03-07 | 2019-09-12 | Wealth Wizards Limited | Method, system and computer program product for providing automated advice |
CN110647631A (en) * | 2018-06-25 | 2020-01-03 | 阿里巴巴集团控股有限公司 | Case recommendation method and device, storage medium and processor |
CN110716957A (en) * | 2019-09-23 | 2020-01-21 | 珠海市新德汇信息技术有限公司 | Intelligent mining and analyzing method for class case suspicious objects |
CN110717041A (en) * | 2019-09-19 | 2020-01-21 | 太极计算机股份有限公司 | Case retrieval method and system |
CN110727787A (en) * | 2019-10-11 | 2020-01-24 | 北京明略软件***有限公司 | Case text matching method and device, electronic equipment and storage medium |
US20200090155A1 (en) * | 2018-09-18 | 2020-03-19 | Fuji Xerox Co., Ltd. | Information processing apparatus and non-transitory computer readable medium storing program |
CN110909542A (en) * | 2019-11-15 | 2020-03-24 | 珠海市新德汇信息技术有限公司 | Intelligent semantic series-parallel analysis method and system |
CN110928994A (en) * | 2019-11-28 | 2020-03-27 | 北京华宇元典信息服务有限公司 | Similar case retrieval method, similar case retrieval device and electronic equipment |
-
2020
- 2020-06-05 CN CN202010506263.5A patent/CN111666495B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160350377A1 (en) * | 2015-05-29 | 2016-12-01 | International Business Machines Corporation | Estimating the cost of data-mining services |
CN110020134A (en) * | 2017-11-09 | 2019-07-16 | 北京国双科技有限公司 | A kind of method for pushing, system, storage medium and the processor of knowledge services information |
CN108280149A (en) * | 2018-01-04 | 2018-07-13 | 东南大学 | A kind of doctor-patient dispute class case recommendation method based on various dimensions tag along sort |
WO2019171040A1 (en) * | 2018-03-07 | 2019-09-12 | Wealth Wizards Limited | Method, system and computer program product for providing automated advice |
CN110647631A (en) * | 2018-06-25 | 2020-01-03 | 阿里巴巴集团控股有限公司 | Case recommendation method and device, storage medium and processor |
US20200090155A1 (en) * | 2018-09-18 | 2020-03-19 | Fuji Xerox Co., Ltd. | Information processing apparatus and non-transitory computer readable medium storing program |
CN109783640A (en) * | 2018-12-20 | 2019-05-21 | 广州恒巨信息科技有限公司 | One type case recommended method, system and device |
CN110717041A (en) * | 2019-09-19 | 2020-01-21 | 太极计算机股份有限公司 | Case retrieval method and system |
CN110716957A (en) * | 2019-09-23 | 2020-01-21 | 珠海市新德汇信息技术有限公司 | Intelligent mining and analyzing method for class case suspicious objects |
CN110727787A (en) * | 2019-10-11 | 2020-01-24 | 北京明略软件***有限公司 | Case text matching method and device, electronic equipment and storage medium |
CN110909542A (en) * | 2019-11-15 | 2020-03-24 | 珠海市新德汇信息技术有限公司 | Intelligent semantic series-parallel analysis method and system |
CN110928994A (en) * | 2019-11-28 | 2020-03-27 | 北京华宇元典信息服务有限公司 | Similar case retrieval method, similar case retrieval device and electronic equipment |
Non-Patent Citations (2)
Title |
---|
SHAOHUA GAO; JIA SONG; YUNQIANG ZHU; CHENYAN MA: "Association and Recomendation for Geosciences Data Attributes Based on Semantic Similarity Measurement", 2018 7TH INTERNATIONAL CONFERENCE ON AGRO-GEOINFORMATICS (AGRO-GEOINFORMATICS) * |
唐华;杨解君;王俊;黄炜;: "基于K近邻分类算法的涉恐信息过滤模型研究", 情报杂志, no. 03 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112015774A (en) * | 2020-09-25 | 2020-12-01 | 北京百度网讯科技有限公司 | Chart recommendation method and device, electronic equipment and storage medium |
CN112015774B (en) * | 2020-09-25 | 2023-08-29 | 北京百度网讯科技有限公司 | Chart recommending method and device, electronic equipment and storage medium |
CN112348714A (en) * | 2020-11-05 | 2021-02-09 | 科大讯飞股份有限公司 | Evidence chain construction method, electronic device and storage medium |
CN112925899A (en) * | 2021-02-09 | 2021-06-08 | 重庆中科云从科技有限公司 | Ranking model establishing method, case clue recommending device and medium |
CN113947290A (en) * | 2021-09-26 | 2022-01-18 | 海南电网有限责任公司 | Distribution network evaluation and review auxiliary method and system based on artificial intelligence |
Also Published As
Publication number | Publication date |
---|---|
CN111666495B (en) | 2023-08-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111666495A (en) | Case recommendation method, device, equipment and storage medium | |
CN111507104B (en) | Method and device for establishing label labeling model, electronic equipment and readable storage medium | |
CN111104514A (en) | Method and device for training document label model | |
CN112735124B (en) | Traffic data analysis method, device, equipment, vehicle and storage medium | |
CN112036509A (en) | Method and apparatus for training image recognition models | |
US20160063376A1 (en) | Obtaining user traits | |
CN111858905B (en) | Model training method, information identification device, electronic equipment and storage medium | |
CN110427436B (en) | Method and device for calculating entity similarity | |
CN111078878A (en) | Text processing method, device and equipment and computer readable storage medium | |
CN111538815A (en) | Text query method, device, equipment and storage medium | |
CN112380847A (en) | Interest point processing method and device, electronic equipment and storage medium | |
CN111090991A (en) | Scene error correction method and device, electronic equipment and storage medium | |
CN110569370B (en) | Knowledge graph construction method and device, electronic equipment and storage medium | |
CN112560499A (en) | Pre-training method and device of semantic representation model, electronic equipment and storage medium | |
CN111666771A (en) | Semantic label extraction device, electronic equipment and readable storage medium of document | |
CN111563198A (en) | Material recall method, device, equipment and storage medium | |
CN111783998A (en) | Illegal account recognition model training method and device and electronic equipment | |
CN110796191A (en) | Trajectory classification method and device | |
CN110909136A (en) | Satisfaction degree estimation model training method and device, electronic equipment and storage medium | |
CN112052390A (en) | Resource screening method and device, electronic equipment and storage medium | |
CN111666417A (en) | Method and device for generating synonyms, electronic equipment and readable storage medium | |
CN111858880A (en) | Method and device for obtaining query result, electronic equipment and readable storage medium | |
CN112148979B (en) | Event-associated user identification method, device, electronic equipment and storage medium | |
CN111125445A (en) | Community theme generation method and device, electronic equipment and storage medium | |
CN111177479A (en) | Method and device for acquiring feature vectors of nodes in relational network graph |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |