CN116913460A - Marketing business compliance judgment and analysis method for pharmaceutical instruments and inspection reagents - Google Patents
Marketing business compliance judgment and analysis method for pharmaceutical instruments and inspection reagents Download PDFInfo
- Publication number
- CN116913460A CN116913460A CN202311177289.XA CN202311177289A CN116913460A CN 116913460 A CN116913460 A CN 116913460A CN 202311177289 A CN202311177289 A CN 202311177289A CN 116913460 A CN116913460 A CN 116913460A
- Authority
- CN
- China
- Prior art keywords
- marketing
- vertex
- layer
- representing
- information
- 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
- 239000003153 chemical reaction reagent Substances 0.000 title claims abstract description 10
- 238000004458 analytical method Methods 0.000 title claims description 4
- 238000007689 inspection Methods 0.000 title description 2
- 238000000034 method Methods 0.000 claims abstract description 33
- 230000002159 abnormal effect Effects 0.000 claims abstract description 16
- 239000003814 drug Substances 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 53
- 230000006399 behavior Effects 0.000 claims description 27
- 238000006116 polymerization reaction Methods 0.000 claims description 13
- 230000002776 aggregation Effects 0.000 claims description 11
- 238000004220 aggregation Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 6
- 230000001737 promoting effect Effects 0.000 claims description 6
- 239000003795 chemical substances by application Substances 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 230000003042 antagnostic effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012946 outsourcing Methods 0.000 description 1
Classifications
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Medicinal Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of marketing business management, and discloses a marketing business compliance judging and analyzing method of a medicine instrument and a checking reagent, which comprises the following steps: step 101, collecting marketing business information; 102, identifying an entity from the marketing business information by an entity identification method; step 103, generating graph information; 104, inputting a first model according to the vertex characteristics and the graph information, fusing the vertex characteristics by the first model, updating the vertex characteristics to obtain vertex updating characteristics, and outputting a result representing whether the marketing behavior of a marketing company on a marketing product is abnormal; the method and the system can find potential marketing abnormal based on the recorded marketing business information.
Description
Technical Field
The invention relates to the technical field of marketing business management, in particular to a marketing business compliance judging and analyzing method for a medicine instrument and a checking reagent.
Background
Along with the supervision informatization and the flow of the medicine marketing, the flow requires the flow management of all links of the marketing business, and the records of the notes, the contracts and the behaviors are unified, but only the contents uploaded by marketing personnel can be recorded, the fiction of the contents can not be controlled, the judgment task of the compliance of the marketing business is changed from the judgment of the compliance of the flow on the surface to the judgment of the compliance of the marketing contents and the behaviors, and the abnormality of the actual marketing behaviors can not be identified by the unified judgment method of the records of the notes, the contracts and the behaviors.
Disclosure of Invention
The invention provides a marketing business compliance judging and analyzing method for a medicine instrument and a checking reagent, which solves the technical problem that the existing judging method in the related technology cannot identify the abnormality of the actual marketing behavior.
The invention provides a marketing business compliance judging and analyzing method for a medicine instrument and a test reagent, which comprises the following steps:
step 101, collecting marketing business information;
102, identifying an entity from the marketing business information by an entity identification method;
step 103, generating graph information, wherein the graph information comprises vertex sets and edge sets, the vertices in the vertex sets are in one-to-one correspondence with the entities in the step 102, and a relationship exists between the entities corresponding to the two vertices connected by the edge; encoding the entity to generate vertex characteristics;
and 104, inputting a first model according to the vertex characteristics and the graph information, fusing the vertex characteristics by the first model, updating the vertex characteristics to obtain vertex updating characteristics, and outputting a result representing whether the marketing behavior of the marketing company on the marketing product is abnormal.
Further, the marketing information includes contract flow information, business flow information, bill flow information, and fund flow information.
Further, the entities include the following categories: enterprise name, hospital name, marketing product name, marketing cost, marketer name, promotional personnel occupation name, promotional personnel position name, promotional cost, customer name.
Further, the entity is identified and the relationship is extracted, so that the relationship among the entities is obtained, and the extracted relationship has the relationship attribute or does not have the relationship attribute.
Further, the full connection layer of the first model outputs two classifications, and the two classification labels respectively correspond to whether the marketing company has abnormality or not for the marketing behavior of the marketing product.
Further, the first model comprises a polymerization layer and a full-connection layer, the polymerization layer fuses the vertex characteristics with each other, and the vertex characteristics are updated to obtain vertex updating characteristics.
Further, the first model comprises a polymerization layer, a generation layer, a logic layer and a full connection layer, wherein the polymerization layer fuses the vertex characteristics with each other, and updates the vertex characteristics to obtain vertex update characteristics;
the generation layer is used for inputting the vertex updating characteristic, outputting a first adjacent matrix, the logic layer inputs the first adjacent matrix and a second adjacent matrix, performing point-to-point difference on the first adjacent matrix and the second adjacent matrix to obtain a third adjacent matrix, the second adjacent matrix represents the connection relation of the vertices in the diagram information, the full connection layer inputs the third adjacent matrix, and the result representing whether marketing behaviors of marketing companies on marketing products are abnormal is output.
Further, the calculation formula of the logic layer is as follows:wherein->、/>、/>Respectively represent a first adjacent matrix, a second adjacent matrix and a third adjacent matrixElements of row a and column b of the matrix,/->Weight parameters representing logical layers, +.>Representing bias parameters of the logic layer; the second adjacency matrix is a representation of the connection relation of vertices in the graph information.
Further, the aggregation layer and the generation layer are pre-trained, in the pre-training process, a judging layer is connected, the judging layer inputs a first adjacent matrix or a second adjacent matrix, the output of the judging layer is divided into two categories, one category corresponds to the judgment result as the input of the first adjacent matrix, and the other category corresponds to the judgment result as the input of the second adjacent matrix.
Further, the calculation formula of the aggregation layer is as follows:wherein->Vertex update feature representing the ith vertex, < ->Aggregation index indicating the ith vertex, +.>Representing the set of vertices with edges present with the ith vertex,/->Representing a nonlinear activation function +.>Representing a second weight, ++>Vertex features representing the jth vertex; the calculation formula of the aggregation index of the ith vertex is as follows:wherein->,,/>And->Vertex characteristics of the ith and j-th vertices, respectively,>representing a first weight, ++>Representing a third weight, T representing a transpose, < ->Represents the natural exponential function, leakyRelu represents the LeakyRelu activation function,/->Representing the set of vertices that have edges with the ith vertex.
The invention has the beneficial effects that: according to the method and the device, the combined probability distribution of the abnormal marketing behaviors of the marketing products under the condition of the marketing business information is learned, and the learned result is applied to the marketing business information to be predicted to obtain the result whether the abnormal marketing behaviors of the marketing products exist or not, so that potential marketing behavior abnormalities can be found based on the recorded marketing business information.
Drawings
FIG. 1 is a flow chart of a method of compliance judgment analysis of a marketing business of a pharmaceutical instrument and a test agent of the present invention.
Detailed Description
The subject matter described herein will now be discussed with reference to example embodiments. It is to be understood that these embodiments are merely discussed so that those skilled in the art may better understand and implement the subject matter described herein and that changes may be made in the function and arrangement of the elements discussed without departing from the scope of the disclosure herein. Various examples may omit, replace, or add various procedures or components as desired. In addition, features described with respect to some examples may be combined in other examples as well.
As shown in fig. 1, a marketing business compliance judging and analyzing method of a medicine instrument and a test reagent comprises the following steps:
step 101, collecting marketing business information, wherein the marketing information comprises contract flow information, business flow information, bill flow information and fund flow information;
wherein the contract flow information comprises information of marketing outsourcing contracts, task issuing contracts and task crowd-in equal contracts,
the service flow information comprises contractual task information, task allocation information, acquisition task information, completion task information and performance evaluation information, wherein the contractual task information comprises total package task information and total package budget information;
the allocation task information comprises subcontracting task information and subcontracting budget information;
the task information comprises task personnel information, work plan information and work budget information;
the completion task information includes work plan completion information;
the performance evaluation information comprises work process evaluation information and work result evaluation information;
in general, the traffic flow information contains all of the information in the marketing campaign.
Bill flow information includes information of bills related to fund settlement;
the funds flow information includes information relating to the funds flow.
The marketing business information of the same marketing company is collected in step 101.
Step 102, identifying an entity from the marketing business information by an entity identification method, wherein the entity comprises the following categories: business name, hospital name, marketing product name, marketing cost marketing personnel name, popularization personnel occupation name the job name of the popularization person, the popularization cost, the customer name (the customer refers to the personnel of the hospital visited by the marketing personnel in general), the customer name,
It is to be noted that the marketing personnel are not popularization personnel, and the marketing personnel belong to marketing enterprises, and the popularization personnel are responsible for carrying out popularization activities.
For some numerical class entities, the number scale of the entities can be reduced by setting identification rules, for example, for a marketing fee class entity, the identification rules are that marketing fees with values within 1 ten thousand to 3 ten thousand are identified as the marketing fee class entity;
and the entity is identified, and meanwhile, the relation extraction is carried out, so that the relation between the entities is obtained, and the extracted relation can have relation attributes or not, and at least can express whether the entity has a real relation.
The above entity identification and relationship extraction may be done manually or using an algorithmic model.
Step 103, generating graph information, wherein the graph information comprises vertex sets and edge sets, the vertices in the vertex sets are in one-to-one correspondence with the entities in the step 102, and a relationship exists between the entities corresponding to the two vertices connected by the edge; encoding the entity to generate vertex characteristics;
the invention provides a method for entity coding, which is based on entity set for single-hot coding.
The invention provides a method for encoding an entity, which encodes the entity based on a word embedding model.
104, inputting a first model according to the vertex characteristics and the graph information, fusing the vertex characteristics by the first model, updating the vertex characteristics to obtain vertex updating characteristics, and outputting a result representing whether the marketing behavior of a marketing company on a marketing product is abnormal;
in one embodiment of the invention, two categories are output, two category labels corresponding to the presence and absence of anomalies in marketing activity of the marketing company for the marketing product, respectively.
The model can learn the abnormal joint probability distribution of the marketing behaviors of the marketing products under the condition of marketing business information, and apply the learned results to the marketing business information to be predicted to obtain whether the abnormal marketing behaviors of the marketing products exist or not.
In general, the marketing behavior of the marketing products of the same class should be similar, and if the marketing behavior deviating from the distribution rule occurs, the marketing company is indicated to have abnormality on the marketing behavior of the marketing products. The specific behavior abnormality may be expressed in various ways, for example, the task staff and work plan may be received in a fictional manner, the funds are transferred to the user, and the abnormality cannot be represented in the business flow information. The invention provides a first model, which comprises a polymerization layer and a full-connection layer, wherein the calculation formula of the polymerization layer is as follows:wherein->Vertex update feature representing the ith vertex, < ->Aggregation index indicating the ith vertex, +.>Representing the set of vertices with edges present with the ith vertex,/->Representing a nonlinear activation function +.>Representing a second weight, ++>Vertex features representing the jth vertex; the calculation formula of the aggregation index of the ith vertex is as follows:wherein->,,/>And->Vertex characteristics of the ith and j-th vertices, respectively,>representing a first weight, ++>Representing a third weight, T representing a transpose, < ->Represents the natural exponential function, leakyRelu represents the LeakyRelu activation function,/->Representing a set of vertices that have edges with the ith vertex; the full connection layer inputs the vertex update feature representing the marketing product and outputs a result representing whether the marketing company's marketing behavior for the marketing product is abnormal.
The invention provides a second first model, which comprises a polymerization layer, a generation layer, a logic layer and a full connection layer, wherein the polymerization layer can be the same as the polymerization layer of the first model, and other calculation methods can be adopted to mutually fuse vertex characteristics;
the generation layer is used for inputting the vertex updating characteristic, outputting a first adjacent matrix, the logic layer inputs the first adjacent matrix and a second adjacent matrix, performing point-to-point difference on the first adjacent matrix and the second adjacent matrix to obtain a third adjacent matrix, the second adjacent matrix represents the connection relation of the vertices in the diagram information, the full connection layer inputs the third adjacent matrix, and the result representing whether the marketing behavior of a marketing company on a marketing product is abnormal is output; most of the abnormal cases are fictitious marketing business information, which does not correspond to the actual marketing activities.
The calculation formula of the generated layer is as follows:
wherein the method comprises the steps ofRepresenting a first adjacency matrix->Representing vertex update feature matrix,/>A combination function representing an S-shaped function and a logistic regression function, wherein the value of the S-shaped function is input into the logistic regression function to output a value of 0 or 1, and one row vector of the vertex updating characteristic matrix represents one vertex updating characteristic; the calculation formula of the logic layer is as follows: />Wherein->、/>、/>Elements of the a-th row and the b-th column of the first adjacent matrix, the second adjacent matrix and the third adjacent matrix are respectively represented;
the calculation formula of the logic layer is as follows:
wherein->、/>、/>Elements of a row a and a column b of the first adjacency matrix, the second adjacency matrix and the third adjacency matrix are respectively represented by +.>Weight parameters representing logical layers, +.>Representing the bias parameters of the logic layer. Increasing the weight parameters improves the performance of the logic layer. Wherein the second adjacency matrix is a representation of the connection relation of vertices in the graph information, +.>A value of 1, indicates that there is an edge between the a-th and b-th vertices,a value of 0 indicates that no edge exists between the a-th and b-th vertices.
In one embodiment of the invention, the generation layer may employ a multi-layer perceptron.
The aggregation layer and the generation layer are pre-trained, a judging layer is connected in the pre-training process, the judging layer inputs a first adjacent matrix or a second adjacent matrix, the output of the judging layer is divided into two categories, one category corresponds to the fact that the judging result is input into the first adjacent matrix, and the other category corresponds to the fact that the judging result is input into the second adjacent matrix.
The discriminating layer may employ a multi-layer perceptron.
Pre-training by the method of generating an antagonistic network, the weight parameters of the new layering are not regenerated when the first model is back-propagated. The training samples in the generation layer pre-training process are samples with normal marketing behavior of the marketing product. Marketing behavior of the marketing product of the training sample is normal and abnormal as a result of judgment after expert investigation.
The generation layer which can restore the vertex connection relation based on the vertex updating characteristics of the normal marketing behaviors is obtained through training of the normal training samples, if the predicted samples are abnormal marketing behaviors, the generation layer cannot restore the vertex connection relation, the restoration difference of the vertex level is calculated through the logic layer, a more accurate judgment result can be obtained through the restoration difference, and the accuracy is higher.
For the second model, the marketing business information of the same marketing product of the same marketing company is collected in step 101.
The embodiment has been described above with reference to the embodiment, but the embodiment is not limited to the above-described specific implementation, which is only illustrative and not restrictive, and many forms can be made by those of ordinary skill in the art, given the benefit of this disclosure, are within the scope of this embodiment.
Claims (10)
1. A marketing business compliance judging and analyzing method for a medicine instrument and a checking reagent is characterized by comprising the following steps:
step 101, collecting marketing business information;
102, identifying an entity from the marketing business information by an entity identification method;
step 103, generating graph information, wherein the graph information comprises vertex sets and edge sets, the vertices in the vertex sets are in one-to-one correspondence with the entities in the step 102, and a relationship exists between the entities corresponding to the two vertices connected by the edge; encoding the entity to generate vertex characteristics;
and 104, inputting a first model according to the vertex characteristics and the graph information, fusing the vertex characteristics by the first model, updating the vertex characteristics to obtain vertex updating characteristics, and outputting a result representing whether the marketing behavior of the marketing company on the marketing product is abnormal.
2. The method of claim 1, wherein the marketing message comprises compliance flow information, business flow information, bill flow information, and fund flow information.
3. The method of claim 1, wherein the entity comprises the following categories: enterprise name, hospital name, marketing product name, marketing cost, marketer name, promotional personnel occupation name, promotional personnel position name, promotional cost, customer name.
4. The method for determining and analyzing compliance of a marketing business of a pharmaceutical apparatus and a test agent according to claim 1, wherein the entity is identified and a relationship is extracted, the relationship is extracted to obtain a relationship between the entities, and the extracted relationship has a relationship attribute or does not have a relationship attribute.
5. The method for judging and analyzing the compliance of a marketing business of a medical instrument and a test reagent according to claim 1, wherein the full-connection layer of the first model outputs two categories, and the two category labels respectively correspond to the presence or absence of abnormality of the marketing company on the marketing behavior of the marketing product.
6. The method for determining and analyzing compliance of a marketing business of a pharmaceutical apparatus and a test agent according to claim 1, wherein the first model comprises a polymerization layer and a full-connection layer, wherein the polymerization layer fuses vertex features with each other, and updates the vertex features to obtain vertex update features.
7. The method for judging and analyzing compliance of marketing business of pharmaceutical equipment and test reagents according to claim 1, wherein the first model comprises a polymerization layer, a generation layer, a logic layer and a full connection layer, wherein the polymerization layer fuses vertex characteristics with each other, and updates the vertex characteristics to obtain vertex update characteristics;
the generation layer is used for inputting the vertex updating characteristic, outputting a first adjacent matrix, the logic layer inputs the first adjacent matrix and a second adjacent matrix, performing point-to-point difference on the first adjacent matrix and the second adjacent matrix to obtain a third adjacent matrix, the second adjacent matrix represents the connection relation of the vertices in the diagram information, the full connection layer inputs the third adjacent matrix, and the result representing whether marketing behaviors of marketing companies on marketing products are abnormal is output.
8. The method for compliance judged analysis of a marketing business of a pharmaceutical instrument and a test agent according to claim 7, wherein the logic layer has the following formula:
wherein->、/>、/>Elements of a row a and a column b of the first adjacency matrix, the second adjacency matrix and the third adjacency matrix are respectively represented by +.>The weight parameters representing the logical layer are represented,representing bias parameters of the logic layer; the second adjacency matrix is a representation of the connection relation of vertices in the graph information.
9. The method according to claim 7, wherein the aggregation layer and the generation layer are pre-trained, the discrimination layer is connected during the pre-training, the discrimination layer inputs the first adjacent matrix or the second adjacent matrix, the output of the discrimination layer is classified into two categories, one category corresponds to the determination result being the input of the first adjacent matrix, and the other category corresponds to the determination result being the input of the second adjacent matrix.
10. The method for determining and analyzing compliance with a marketing business of a pharmaceutical instrument and a test agent according to claim 6 or 7, wherein the calculation formula of the aggregation layer is as follows:wherein->Vertex update feature representing the ith vertex, < ->Aggregation index indicating the ith vertex, +.>Representing the set of vertices with edges present with the ith vertex,/->Representing a nonlinear activation function +.>Representing a second weight, ++>Vertex features representing the jth vertex;
the calculation formula of the aggregation index of the ith vertex is as follows:
wherein->,,/>And->Vertex characteristics of the ith and j-th vertices, respectively,>representing a first weight, ++>Representing a third weight, T representing a transpose, < ->Represents the natural exponential function, leakyRelu represents the LeakyRelu activation function,/->Representing the set of vertices that have edges with the ith vertex.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311177289.XA CN116913460B (en) | 2023-09-13 | 2023-09-13 | Marketing business compliance judgment and analysis method for pharmaceutical instruments and inspection reagents |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311177289.XA CN116913460B (en) | 2023-09-13 | 2023-09-13 | Marketing business compliance judgment and analysis method for pharmaceutical instruments and inspection reagents |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116913460A true CN116913460A (en) | 2023-10-20 |
CN116913460B CN116913460B (en) | 2023-12-29 |
Family
ID=88356874
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311177289.XA Active CN116913460B (en) | 2023-09-13 | 2023-09-13 | Marketing business compliance judgment and analysis method for pharmaceutical instruments and inspection reagents |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116913460B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040093296A1 (en) * | 2002-04-30 | 2004-05-13 | Phelan William L. | Marketing optimization system |
CN109214719A (en) * | 2018-11-02 | 2019-01-15 | 广东电网有限责任公司 | A kind of system and method for the marketing inspection analysis based on artificial intelligence |
CN110929036A (en) * | 2019-11-29 | 2020-03-27 | 南方电网数字电网研究院有限公司 | Electric power marketing inspection management method and device, computer equipment and storage medium |
CN112199526A (en) * | 2020-09-30 | 2021-01-08 | 北京字节跳动网络技术有限公司 | Method and device for issuing multimedia content, electronic equipment and storage medium |
CN112632274A (en) * | 2020-10-29 | 2021-04-09 | 中科曙光南京研究院有限公司 | Abnormal event classification method and system based on text processing |
CN112883062A (en) * | 2021-02-03 | 2021-06-01 | 泽恩科技有限公司 | Self-defined rule checking method not based on rule |
CN112926855A (en) * | 2021-02-24 | 2021-06-08 | 北京通付盾人工智能技术有限公司 | Marketing activity risk control system and method based on knowledge graph |
CN114356982A (en) * | 2021-12-17 | 2022-04-15 | 杭州摸象大数据科技有限公司 | Marketing compliance checking method and device, computer equipment and storage medium |
CN115186099A (en) * | 2022-05-31 | 2022-10-14 | 民生科技有限责任公司 | Marketing and marketing method and system based on multi-dimensional construction knowledge graph |
CN116304216A (en) * | 2023-03-29 | 2023-06-23 | 广西电网有限责任公司 | Marketing domain graph data model construction method based on graph technology |
CN116578717A (en) * | 2023-04-28 | 2023-08-11 | 国网安徽省电力有限公司信息通信分公司 | Multi-source heterogeneous knowledge graph construction method for electric power marketing scene |
-
2023
- 2023-09-13 CN CN202311177289.XA patent/CN116913460B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040093296A1 (en) * | 2002-04-30 | 2004-05-13 | Phelan William L. | Marketing optimization system |
CN109214719A (en) * | 2018-11-02 | 2019-01-15 | 广东电网有限责任公司 | A kind of system and method for the marketing inspection analysis based on artificial intelligence |
CN110929036A (en) * | 2019-11-29 | 2020-03-27 | 南方电网数字电网研究院有限公司 | Electric power marketing inspection management method and device, computer equipment and storage medium |
CN112199526A (en) * | 2020-09-30 | 2021-01-08 | 北京字节跳动网络技术有限公司 | Method and device for issuing multimedia content, electronic equipment and storage medium |
CN112632274A (en) * | 2020-10-29 | 2021-04-09 | 中科曙光南京研究院有限公司 | Abnormal event classification method and system based on text processing |
CN112883062A (en) * | 2021-02-03 | 2021-06-01 | 泽恩科技有限公司 | Self-defined rule checking method not based on rule |
CN112926855A (en) * | 2021-02-24 | 2021-06-08 | 北京通付盾人工智能技术有限公司 | Marketing activity risk control system and method based on knowledge graph |
CN114356982A (en) * | 2021-12-17 | 2022-04-15 | 杭州摸象大数据科技有限公司 | Marketing compliance checking method and device, computer equipment and storage medium |
CN115186099A (en) * | 2022-05-31 | 2022-10-14 | 民生科技有限责任公司 | Marketing and marketing method and system based on multi-dimensional construction knowledge graph |
CN116304216A (en) * | 2023-03-29 | 2023-06-23 | 广西电网有限责任公司 | Marketing domain graph data model construction method based on graph technology |
CN116578717A (en) * | 2023-04-28 | 2023-08-11 | 国网安徽省电力有限公司信息通信分公司 | Multi-source heterogeneous knowledge graph construction method for electric power marketing scene |
Non-Patent Citations (2)
Title |
---|
陈宁;: "基于C/S结构平台的营销信息管理***开发", 西安石油大学学报(自然科学版), no. 01 * |
韦泰丞: "基于时空图神经网络的商品销量预测", 计算机***应用计算机***应用, vol. 32, no. 4, pages 52 - 65 * |
Also Published As
Publication number | Publication date |
---|---|
CN116913460B (en) | 2023-12-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5586373B2 (en) | Computer-readable storage medium storing a program for causing a computer system to realize the function of a component that processes a payment request, and a method of operating a computer system that causes a computer system to process a payment request | |
US20130054259A1 (en) | Rule-based Prediction of Medical Claims' Payments | |
TW200821787A (en) | Device of managing defect, method of managing defect, program of managing defect and recording medium of recoding the program | |
CN106157132A (en) | Credit risk monitoring system and method | |
CN110706039A (en) | Electric vehicle residual value rate evaluation system, method, equipment and medium | |
CN112418738B (en) | Staff operation risk prediction method based on logistic regression | |
Dbouk et al. | Towards a machine learning approach for earnings manipulation detection | |
CN107633455A (en) | Credit estimation method and device based on data model | |
Gordon | Virtual navigation and geospatial mapping tools, customer data analytics, and computer vision and simulation optimization algorithms in the blockchain-based metaverse | |
Agarwal et al. | A seven-layer model with checklists for standardising fairness assessment throughout the AI lifecycle | |
Hu | Predicting and improving invoice-to-cash collection through machine learning | |
CN111626331B (en) | Automatic industry classification device and working method thereof | |
CN116913460B (en) | Marketing business compliance judgment and analysis method for pharmaceutical instruments and inspection reagents | |
CN117114812A (en) | Financial product recommendation method and device for enterprises | |
CN115358875A (en) | Insurance product management system | |
CN115063143A (en) | Account data processing method and device, computer equipment and storage medium | |
Musa | The role of artificial intelligence in achieving auditing quality for small and medium enterprises in the Kingdom of Saudi Arabia | |
Srivastava et al. | Hyperautomation in transforming underwriting operation in the life insurance industry | |
CN112950350A (en) | Loan product recommendation method and system based on machine learning | |
Arora et al. | Prediction of Dynamic Price of Ride-On-Demand Services Using Linear Regression | |
US20240113936A1 (en) | Method and system for artificial intelligence-based acceleration of zero-touch processing | |
CN113570469B (en) | Intelligent vehicle change prediction method for vehicle insurance user | |
JP7231967B1 (en) | Credit risk judgment system and credit risk judgment program | |
Sinha et al. | Implication of soft computing and machine learning method for software quality, defect and model prediction | |
Akbaba et al. | Supplier Performance Evaluation Using Cluster Analysis and Artificial Neural Networks in a MRO Business in Aviation Sector |
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 |