CN114398473A - Enterprise portrait generation method, device, server and storage medium - Google Patents
Enterprise portrait generation method, device, server and storage medium Download PDFInfo
- Publication number
- CN114398473A CN114398473A CN202210059097.8A CN202210059097A CN114398473A CN 114398473 A CN114398473 A CN 114398473A CN 202210059097 A CN202210059097 A CN 202210059097A CN 114398473 A CN114398473 A CN 114398473A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- target
- information
- keywords
- keyword
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000003860 storage Methods 0.000 title claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 230000011218 segmentation Effects 0.000 claims description 47
- 230000002996 emotional effect Effects 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 21
- 238000000605 extraction Methods 0.000 claims description 18
- 230000002776 aggregation Effects 0.000 claims description 9
- 238000004220 aggregation Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000012217 deletion Methods 0.000 claims description 8
- 230000037430 deletion Effects 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 8
- 238000013145 classification model Methods 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 8
- 230000008451 emotion Effects 0.000 description 11
- 239000003795 chemical substances by application Substances 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000014509 gene expression Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013598 vector Substances 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/381—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using identifiers, e.g. barcodes, RFIDs
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Library & Information Science (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application is suitable for the technical field of artificial intelligence, and provides an enterprise portrait generation method, an enterprise portrait generation device, a server and a storage medium, wherein the method comprises the following steps: acquiring enterprise information of a target enterprise, and performing data preprocessing on the enterprise information to obtain target information; extracting keywords from the target information to obtain a target keyword set aiming at the target information; generating enterprise tags of target enterprises based on the target keyword set and the attribute information of each keyword in the target keyword set; and generating an enterprise portrait of the target enterprise according to the enterprise tags of the target enterprise. The enterprise label can be generated based on the attribute information of each keyword in the enterprise information of the target enterprise, so that the enterprise portrait of the target enterprise is constructed by adopting the generated enterprise label, and the accuracy of the constructed enterprise portrait is improved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to an enterprise portrait generation method, an enterprise portrait generation device, a server and a storage medium.
Background
Garbage collection and transportation refers to the collection and transportation of garbage. The garbage can be collected and transported in various ways, such as community domestic garbage, construction garbage and muck, and the places where garbage needs to be cleared are various, such as factories, shopping malls, hotels, construction sites, schools, entertainment places, training centers and the like. At present, most garbage collection and transportation enterprises are on the market, the mode of selecting the garbage collection and transportation enterprises is usually manual selection, and the manual selection mode has high randomness, so that the garbage collection and transportation enterprises meeting the requirements of users are difficult to select from a plurality of garbage collection and transportation enterprises.
In summary, in order to select an enterprise satisfying user requirements from a plurality of enterprises in the related art, an enterprise portrait needs to be constructed for an enterprise, such as a garbage collection and transportation enterprise, so as to accurately select the enterprise based on the enterprise portrait.
Disclosure of Invention
In view of this, embodiments of the present application provide an enterprise representation generation method, apparatus, server and storage medium, so as to solve the problem in the related art that it is difficult to select an enterprise that meets user requirements from a plurality of enterprises.
A first aspect of an embodiment of the present application provides an enterprise portrait generation method, including:
acquiring enterprise information of a target enterprise, and performing data preprocessing on the enterprise information to obtain the target information, wherein the data preprocessing comprises at least one of the following steps: data cleaning, data aggregation, data deletion and data conversion;
extracting keywords from the target information to obtain a target keyword set aiming at the target information;
generating an enterprise tag of a target enterprise based on the target keyword set and attribute information of each keyword in the target keyword set, wherein the attribute information of the keyword comprises at least one of the following items: the keywords themselves, semantic information of the keywords, and the occurrence times of the keywords;
and generating an enterprise portrait of the target enterprise according to the enterprise tags of the target enterprise.
Further, extracting keywords from the target information to obtain a target keyword set for the target information, including:
inputting the target information into a pre-trained keyword extraction model to obtain keywords included by the target information, and storing the obtained keywords into a target keyword set.
Further, extracting keywords from the target information to obtain a target keyword set for the target information, including:
and extracting a target entity from the target information to obtain the target entity included in the target information, and storing the extracted target entity as a keyword into a target keyword set.
Further, generating an enterprise tag of the target enterprise based on the target keyword set and attribute information of each keyword in the target keyword set, including:
and when the attribute information of the keywords comprises the keywords, aiming at each keyword in the target keyword set, comparing the corresponding keyword with a preset keyword set, and if the corresponding keyword belongs to the preset keyword set, determining the corresponding keyword as an enterprise tag of the target enterprise.
Further, generating an enterprise tag of the target enterprise based on the target keyword set and attribute information of each keyword in the target keyword set, including:
when the attribute information of the keywords comprises the semantic information of the keywords and the occurrence times of the keywords, aiming at each keyword in the target keyword set, selecting a plurality of keywords with similar semantics with the corresponding keywords from the target keyword set;
and selecting partial keywords meeting preset screening conditions from the multiple keywords based on the occurrence frequency of each selected keyword in the target keyword set, and generating enterprise tags of the target enterprises according to the selected partial keywords.
Further, the method further comprises:
performing label clustering processing on enterprise labels of target enterprises to obtain a plurality of classes and enterprise labels under each class;
and generating enterprise labels aiming at the corresponding categories according to the semantic information of the enterprise labels under the categories.
Further, the method further comprises:
if the enterprise information comprises at least one piece of public sentiment information, carrying out word segmentation processing on the public sentiment information to obtain a plurality of segmentation words and the occurrence times of each segmentation word included in the public sentiment information, and inputting each segmentation word into a pre-trained binary classification model to obtain the sentiment attributes of the corresponding segmentation word, wherein the sentiment attributes comprise positive attributes and negative attributes;
determining the emotional attribute of the public opinion information according to the emotional attribute and the occurrence frequency of each segmentation word included in the public opinion information;
and generating an enterprise label according to the emotional attribute of each public opinion information in the at least one public opinion information.
A second aspect of an embodiment of the present application provides an enterprise representation generating apparatus, including:
the information acquisition unit is used for acquiring enterprise information of a target enterprise and carrying out data preprocessing on the enterprise information to obtain the target information, wherein the data preprocessing comprises at least one of the following steps: data cleaning, data aggregation, data deletion and data conversion;
the information extraction unit is used for extracting keywords from the target information to obtain a target keyword set aiming at the target information;
a tag generating unit, configured to generate an enterprise tag of the target enterprise based on the target keyword set and attribute information of each keyword in the target keyword set, where the attribute information of the keyword includes at least one of the following: the keywords themselves, semantic information of the keywords, and the occurrence times of the keywords;
and the sketch generation unit is used for generating the enterprise sketch of the target enterprise according to each enterprise label of the target enterprise.
Further, the information extraction unit is specifically configured to: inputting the target information into a pre-trained keyword extraction model to obtain keywords included by the target information, and storing the obtained keywords into a target keyword set.
Further, the information extraction unit is specifically configured to: and extracting a target entity from the target information to obtain the target entity included in the target information, and storing the extracted target entity as a keyword into a target keyword set.
Further, the tag generation unit is specifically configured to: and when the attribute information of the keywords comprises the keywords, aiming at each keyword in the target keyword set, comparing the corresponding keyword with a preset keyword set, and if the corresponding keyword belongs to the preset keyword set, determining the corresponding keyword as an enterprise tag of the target enterprise.
Further, the tag generating unit is specifically further configured to:
when the attribute information of the keywords comprises the semantic information of the keywords and the occurrence times of the keywords, aiming at each keyword in the target keyword set, selecting a plurality of keywords with similar semantics with the corresponding keywords from the target keyword set;
and selecting partial keywords meeting preset screening conditions from the multiple keywords based on the occurrence frequency of each selected keyword in the target keyword set, and generating enterprise tags of the target enterprises according to the selected partial keywords.
Further, the device also comprises a first label extension unit. Wherein the first tag extension unit is configured to:
performing label clustering processing on enterprise labels of target enterprises to obtain a plurality of classes and enterprise labels under each class;
and generating enterprise labels aiming at the corresponding categories according to the semantic information of the enterprise labels under the categories.
Further, the apparatus further comprises a second tag expansion unit. Wherein the second tag extension unit is configured to:
if the enterprise information comprises at least one piece of public sentiment information, carrying out word segmentation processing on the public sentiment information to obtain a plurality of segmentation words and the occurrence times of each segmentation word included in the public sentiment information, and inputting each segmentation word into a pre-trained binary classification model to obtain the sentiment attributes of the corresponding segmentation word, wherein the sentiment attributes comprise positive attributes and negative attributes;
determining the emotional attribute of the public opinion information according to the emotional attribute and the occurrence frequency of each segmentation word included in the public opinion information;
and generating an enterprise label according to the emotional attribute of each public opinion information in the at least one public opinion information.
A third aspect of embodiments of the present application provides a server, which includes a memory, a processor, and a computer program stored in the memory and executable on the server, where the processor implements the steps of the enterprise representation generation method provided by the first aspect when executing the computer program.
A fourth aspect of embodiments of the present application provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the steps of the enterprise representation generating method provided by the first aspect.
The enterprise portrait generation method, the enterprise portrait generation device, the server and the storage medium have the following beneficial effects: because the attribute information of each keyword in the enterprise information of the target enterprise can accurately depict the target enterprise, and the enterprise label is generated based on the attribute information of each keyword in the enterprise information of the target enterprise, the enterprise portrait of the target enterprise is constructed by adopting the generated enterprise label, and the accuracy of the constructed enterprise portrait is improved. The enterprise is selected based on the accurate enterprise image, and the accuracy of selecting the enterprise can be improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the embodiments or the related technical descriptions will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flowchart illustrating an implementation of an enterprise representation generation method according to an embodiment of the present disclosure;
FIG. 2 is a flowchart illustrating an implementation of another method for generating an enterprise representation according to an embodiment of the present disclosure;
FIG. 3 is a flowchart illustrating an implementation of another method for generating an enterprise representation according to an embodiment of the present disclosure;
FIG. 4 is a block diagram of an enterprise representation generating apparatus according to an embodiment of the present disclosure;
fig. 5 is a block diagram of a server according to an embodiment of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
In the embodiment of the application, the enterprise portrait is constructed based on an artificial intelligence technology.
The enterprise representation generation method according to the embodiment of the application can be executed by a server. When the enterprise representation generation method is executed by the server, the execution subject is the server.
It should be noted that the server may include, but is not limited to, a server, a computer, a mobile phone, a tablet, a wearable smart device, and the like. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a web service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform.
Referring to fig. 1, fig. 1 shows a flowchart of an implementation of an enterprise portrait generation method according to an embodiment of the present application, including:
Wherein the data preprocessing may include, but is not limited to, at least one of: data cleaning, data aggregation, data deletion and data conversion. Among other things, the above-described data cleansing is typically used to desensitize data to specified information, such as name information. Data aggregation is commonly used to consolidate multiple pieces of information. Data pruning is typically used to remove redundant data. Data transformation is typically used to transform data into structured data.
The target enterprise can be various enterprises, such as garbage collection and transportation enterprises. The business information may include various information of the target business, such as business official information, public opinion information, evaluation information, and the like.
Here, the execution subject may obtain the enterprise information of the target enterprise through various ways, for example, may obtain the business management information, the intellectual property related information, and the like of the enterprise through a network. Here, the execution subject may use various data preprocessing methods to preprocess the enterprise information to obtain the preprocessed enterprise information, and for convenience of description, the preprocessed enterprise information is referred to as target information.
And 102, extracting keywords from the target information to obtain a target keyword set aiming at the target information.
Here, the execution body may perform keyword extraction on the target information, thereby extracting a set of keywords included in the target information, and for convenience of description, the set of keywords may be referred to as a target keyword set.
Optionally, the extracting the keywords from the target information to obtain a target keyword set for the target information may include: inputting the target information into a pre-trained keyword extraction model to obtain keywords included by the target information, and storing the obtained keywords into a target keyword set.
The keyword extraction model can be used for analyzing the corresponding relation between information and keywords included in the information. Specifically, the keyword extraction model may be a correspondence table that is generated based on statistics of a large amount of information and stores a correspondence between information and a keyword included in the information, or may be a model obtained by training an initial model (for example, a Convolutional Neural Network (CNN), a residual error Network (ResNet), or the like) by a machine learning method based on a training sample.
Here, the execution agent may input the target information into a keyword extraction model trained in advance to obtain keywords included in the target information, and then store the obtained keywords into the target keyword set. It should be noted that, by default, the set of target keywords is an empty set.
Optionally, the extracting the keywords from the target information to obtain a target keyword set for the target information may also include: and extracting a target entity from the target information to obtain the target entity included in the target information, and storing the extracted target entity as a keyword into a target keyword set.
The target entity is usually a preset entity, for example, may be "high and new enterprise", "unit of major concern", or the like.
Here, the execution agent may directly determine whether a target entity exists from the target information, and if so, store the target entity as a keyword into the target keyword set. In addition, the execution subject may also perform entity segmentation on the target information to obtain a plurality of entities, and if the obtained entities are target entities, store the entities as keywords in the target keyword set.
And 103, generating enterprise tags of the target enterprises based on the target keyword sets and the attribute information of each keyword in the target keyword sets.
Wherein, the attribute information of the keyword may include but is not limited to at least one of the following: the keywords themselves, semantic information of the keywords, and the number of occurrences of the keywords.
Here, the execution agent may generate a business label of the target business using each keyword and the corresponding attribute information. For example, the keyword itself may be directly used as an enterprise tag, or a keyword with a relatively large number of occurrences may be used as an enterprise tag.
In some optional implementation manners of this embodiment, the generating an enterprise tag of the target enterprise based on the target keyword set and the attribute information of each keyword in the target keyword set may include: and when the attribute information of the keywords comprises the keywords, aiming at each keyword in the target keyword set, comparing the corresponding keyword with a preset keyword set, and if the corresponding keyword belongs to the preset keyword set, determining the corresponding keyword as an enterprise tag of the target enterprise.
The preset keywords in the preset keyword set are usually preset keywords. For example, a predetermined keyword may be "high and new business".
Here, for each keyword in the target keyword set, the executing entity may compare the keyword with a preset keyword set to determine whether the keyword belongs to the preset keyword set, and if so, take the keyword as an enterprise tag.
For example, if the keyword a is "high and new enterprise", the preset keyword set is { high and new enterprise, focus on unit }, and at this time, the keyword a belongs to the preset keyword set, and the keyword a can be directly used as an enterprise tag of the target enterprise.
In some optional implementation manners of this embodiment, the generating an enterprise tag of the target enterprise based on the target keyword set and the attribute information of each keyword in the target keyword set may further include the following steps one to two.
Step one, when the attribute information of the keywords comprises the semantic information of the keywords and the occurrence times of the keywords, aiming at each keyword in a target keyword set, selecting a plurality of keywords with similar semantics with the corresponding keywords from the target keyword set.
The above semantics are similar, which usually means that the semantics are the same or similar. In practical application, the semantics of the two keywords are similar, the cosine similarity between the two vectors corresponding to the two keywords may be greater than a preset similarity threshold, the editing distance between the two keywords may be smaller than a preset editing threshold, or similar situations in other forms, and this embodiment is not particularly limited. The preset similarity threshold is usually a preset value, and the value of the preset similarity threshold is usually greater than 0 and less than 1. The preset editing threshold is usually a preset value, and the value of the preset editing threshold is usually a positive integer.
Here, for each keyword in the target keyword set, the execution subject may select a plurality of keywords having the same or similar semantics as the keyword from the target keyword set.
And secondly, selecting partial keywords meeting preset screening conditions from the multiple keywords based on the occurrence frequency of each selected keyword in the target keyword set, and generating enterprise tags of the target enterprises according to the selected partial keywords.
The preset screening condition is usually a preset selection condition. The preset screening conditions may include, but are not limited to: and selecting keywords of which the corresponding target ratios are greater than the preset ratio and the ranks of the corresponding target ratios belong to a preset ranking interval, wherein the target ratios are the ratios of the occurrence times to the total occurrence times. The preset ratio is usually a preset value, and the value of the preset ratio is usually greater than 0 and less than 1. The predetermined ranking interval is generally a predetermined interval, and may be, for example, a first name to a third name.
As an example, if the target keyword set is { a, B, C, D, E }, where the number of occurrences of the keyword a is 25, the number of occurrences of the keyword B is 20, the number of occurrences of the keyword C is 15, the number of occurrences of the keyword D is 25, and the number of occurrences of the keyword E is 15, if the keywords selected for the keyword a are B and C, then a target ratio of B to C may be calculated, where the target ratio of the keyword B is 0.2, where 0.2 ÷ 20 ÷ 100, and the target ratio of the keyword C is 0.15, where 0.15 ÷ 15 ÷ 100. In this example, when the preset ratio is 0.15 and the preset ranking interval is from the first name to the third name, the target ratio of the keyword B is 0.2, and the keyword B is ranked third in the target keyword set and meets the screening condition.
In practice, the preset selection condition may also be other selection conditions, such as selecting a keyword whose occurrence number is greater than a preset number, and selecting a keyword whose rank of occurrence number belongs to a preset ranking interval.
Here, the execution main body may perform secondary selection from the plurality of keywords obtained by the primary selection according to the occurrence number of each keyword, thereby obtaining fewer and more accurate keywords. In this way, a smaller number of keywords can be analyzed, which helps to reduce the data processing volume.
The executive body may then use the resulting partial keywords to generate a business label for the target business. For example, the type corresponding to each keyword may be used as an enterprise tag. And generating enterprise labels by combining the semantics of the keywords. For example, if the partial keywords include the following three keywords "dirty", "garbage collection and transportation is not timely", and "foul", at this time, the enterprise tag may be generated by combining the semantics of the keywords: "evaluation poor".
It should be noted that the enterprise tag of the target enterprise may be generated in one manner, or may be generated in a combination of manners. When the enterprise label of the target enterprise is generated through combination of multiple modes, the enterprise labels of multiple angles can be obtained, the obtained label information is richer, and the enterprise portrait can be more comprehensively and accurately depicted.
And 104, generating an enterprise portrait of the target enterprise according to the enterprise tags of the target enterprise.
Here, the execution agent may generate a representation of the target enterprise using all enterprise tags. For example, all enterprise tags may be combined to obtain an enterprise representation of the target enterprise. Or selecting a preset number of enterprise labels from all enterprise labels, and combining the preset number of enterprise labels to obtain the enterprise image.
According to the method provided by the embodiment, the target enterprise can be accurately depicted according to the attribute information of each keyword in the enterprise information of the target enterprise, and the enterprise label is generated based on the attribute information of each keyword in the enterprise information of the target enterprise, so that the enterprise portrait of the target enterprise is constructed by adopting the generated enterprise label, and the accuracy of the constructed enterprise portrait is improved. The enterprise is selected based on the accurate enterprise image, and the accuracy of selecting the enterprise can be improved.
Referring to fig. 2, fig. 2 is a flowchart illustrating an implementation of an enterprise portrait generation method according to an embodiment of the present disclosure. The method for generating the enterprise portrait provided by the embodiment may include the following steps:
Wherein the data preprocessing comprises at least one of: data cleaning, data aggregation, data deletion and data conversion.
Wherein the attribute information of the keyword includes at least one of: the keywords themselves, semantic information of the keywords, and the number of occurrences of the keywords.
In the present embodiment, the specific operations of steps 201-203 are substantially the same as the operations of steps 101-103 in the embodiment shown in fig. 1, and are not repeated herein.
And 204, performing label clustering processing on the enterprise labels of the target enterprises to obtain a plurality of classes and enterprise labels under each class.
The label clustering process is generally used for classifying and dividing enterprise labels. For example, it can be divided into 3 categories.
Here, the executing entity may perform tag clustering processing on all tags of the target enterprise to implement classification of enterprise tags into multiple categories. With multiple enterprise tags under each category.
Here, for each category, the execution agent may generate an enterprise tag corresponding to the category based on semantic information of each enterprise tag in the category. For example, all enterprise tags under the category may be input into a pre-trained neural network model to obtain a total enterprise tag for all enterprise tags under the category.
And step 206, generating an enterprise portrait of the target enterprise according to the enterprise tags of the target enterprise.
In this embodiment, the specific operation of step 206 is substantially the same as the operation of step 104 in the embodiment shown in fig. 1, and is not described herein again.
It should be noted that, since there may be common expressions of meanings of a plurality of enterprise tags, for example, the following three enterprise tags "garbage collection and transportation capability is strong", "garbage disposal method is advanced", and "garbage disposal speed is fast", the common expressions of the three tags are: the self-ability of the enterprise is stronger. Therefore, the executing agent may perform secondary tagging on the obtained enterprise tags, that is, perform clustering on all enterprise tags to obtain a plurality of categories, and generate a whole enterprise tag based on the attribute expressed by each category, for example, based on "garbage collection and transportation capability is strong", "garbage disposal method is advanced", "garbage disposal speed is fast", and "self capability of the enterprise is strong". Therefore, the generated enterprise label can be more accurate and richer. The method is favorable for better describing and depicting the enterprise portrait of the target enterprise.
Referring to fig. 3, fig. 3 is a flowchart illustrating an implementation of an enterprise portrait generation method according to an embodiment of the present disclosure. The method for generating the enterprise portrait provided by the embodiment may include the following steps:
Wherein the data preprocessing comprises at least one of: data cleaning, data aggregation, data deletion and data conversion.
Wherein the attribute information of the keyword includes at least one of: the keywords themselves, semantic information of the keywords, and the number of occurrences of the keywords.
In the present embodiment, the specific operations of steps 301-303 are substantially the same as the operations of steps 101-103 in the embodiment shown in fig. 1, and are not described herein again.
Wherein the emotional attribute comprises a positive attribute and a negative attribute.
The two-classification model is used for determining the emotion attribute of the input segmentation word to be a positive attribute or a negative attribute.
Here, the execution main body may perform a segmentation process on the public opinion information for each public opinion information, thereby obtaining a segmentation included in the public opinion information and the number of occurrences of the segmentation in the public opinion information. Then, for each segmented word, the executing body can input the segmented word into a binary model to obtain the emotion of the corresponding segmented word.
In practice, the execution main body can perform word segmentation processing on the public sentiment information in various word segmentation modes. For example, the execution subject may perform word segmentation processing on public sentiment information by using a shortest Path word segmentation method (N-Short Path). For another example, the execution main body may perform word segmentation processing on the public opinion information by using Maximum Probability word segmentation (Maximum Probability). For another example, the executive body may also perform word segmentation processing on the public sentiment information by using a Maximum Matching method (Maximum Matching).
And 305, determining the emotional attribute of the public sentiment information according to the emotional attribute and the occurrence frequency of each segmentation word included in the public sentiment information.
In practice, after obtaining the emotion attribute of each segment, a comprehensive value is usually calculated based on the emotion attribute of each segment and the corresponding weight of the emotion attribute, and the comprehensive value is used for indicating the emotion attribute of a piece of public opinion information.
For example, if a piece of public sentiment information includes three segmentations, which are "dirty", "noise" and "convenience", respectively, if "dirty" appears 10 times, "noise" appears 15 times, "convenience" appears 20 times, the emotional attribute of "dirty" is a negative attribute, the emotional attribute of "noise" is a negative attribute, the emotional attribute of "convenience" is a positive attribute, and if the weight corresponding to the positive attribute is 0.4 and the weight corresponding to the negative attribute is 0.6, the emotional attribute of the piece of public sentiment information is a negative attribute. Wherein-10 × 0.6-15 × 0.6+20 × 0.4 ═ -7, which is a negative value, belongs to the negative attribute.
And 306, generating an enterprise label according to the emotional attribute of each public opinion information in the at least one public opinion information.
Here, the executing body may obtain the enterprise tag based on the emotional attributes of all the public opinion information, for example, if there are 100 pieces of public opinion information, 80 pieces of public opinion information have negative emotional attributes, and 20 pieces of public opinion information have positive emotional attributes, the credit level of the enterprise may not be high, and the enterprise tag may be generated as "low credibility".
And 307, generating an enterprise portrait of the target enterprise according to the enterprise tags of the target enterprise.
In this embodiment, the specific operation of step 307 is substantially the same as the operation of step 104 in the embodiment shown in fig. 1, and is not repeated herein.
According to the embodiment, richer and more accurate enterprise tags for the target enterprise can be obtained, and the enterprise portrait of the target enterprise can be better described and depicted, so that the accuracy of the generated enterprise portrait is further improved.
Referring to fig. 4, fig. 4 is a block diagram illustrating an enterprise representation generating apparatus 400 according to an embodiment of the present disclosure. The enterprise representation generating device in this embodiment comprises units for performing the steps in the embodiments corresponding to fig. 1-3. Please refer to fig. 1-3 and the related descriptions of the embodiments corresponding to fig. 1-3. For convenience of explanation, only the portions related to the present embodiment are shown. Referring to FIG. 4, an enterprise representation generation apparatus 400 includes:
an information obtaining unit 401, configured to obtain enterprise information of a target enterprise, and perform data preprocessing on the enterprise information to obtain the target information, where the data preprocessing includes at least one of the following: data cleaning, data aggregation, data deletion and data conversion;
an information extraction unit 402, configured to perform keyword extraction on target information to obtain a target keyword set for the target information;
a tag generating unit 403, configured to generate an enterprise tag of the target enterprise based on the target keyword set and attribute information of each keyword in the target keyword set, where the attribute information of the keyword includes at least one of the following: the keywords themselves, semantic information of the keywords, and the occurrence times of the keywords;
and a representation generating unit 404, configured to generate an enterprise representation of the target enterprise according to each enterprise tag of the target enterprise.
Here, the execution subject may obtain the enterprise information of the target enterprise through various ways, for example, may obtain the business management information, the intellectual property related information, and the like of the enterprise through a network. Then, the execution subject may use various data preprocessing methods to preprocess the enterprise information to obtain the preprocessed enterprise information, which is denoted as target information for convenience of description.
Then, the executing entity may perform keyword extraction on the target information, so as to extract a set of keywords included in the target information, which is referred to as a target keyword set for convenience of description. Wherein, the attribute information of the keyword may include but is not limited to at least one of the following: the keywords themselves, semantic information of the keywords, and the number of occurrences of the keywords.
Then, the execution body may generate an enterprise tag of the target enterprise by using each keyword and the corresponding attribute information. For example, the keyword itself may be directly used as an enterprise tag, or a keyword with a relatively large number of occurrences may be used as an enterprise tag.
Finally, the executive agent may use all enterprise tags to generate a representation of the target enterprise. For example, all enterprise tags may be combined to obtain an enterprise representation of the target enterprise. Or selecting a preset number of enterprise labels from all enterprise labels, and combining the preset number of enterprise labels to obtain the enterprise image.
According to the device provided by the embodiment, the target enterprise can be accurately depicted according to the attribute information of each keyword in the enterprise information of the target enterprise, and the enterprise label is generated based on the attribute information of each keyword in the enterprise information of the target enterprise, so that the enterprise portrait of the target enterprise is constructed by adopting the generated enterprise label, and the accuracy of the constructed enterprise portrait is improved. The enterprise is selected based on the accurate enterprise image, and the accuracy of selecting the enterprise can be improved.
As an embodiment of the present application, the information extracting unit 402 is specifically configured to: inputting the target information into a pre-trained keyword extraction model to obtain keywords included by the target information, and storing the obtained keywords into a target keyword set.
Here, the execution agent may input the target information into a keyword extraction model trained in advance to obtain keywords included in the target information, and then store the obtained keywords into the target keyword set. It should be noted that, by default, the set of target keywords is an empty set.
As an embodiment of the present application, the information extracting unit 402 is specifically configured to: and extracting a target entity from the target information to obtain the target entity included in the target information, and storing the extracted target entity as a keyword into a target keyword set.
Here, the execution agent may directly determine whether a target entity exists from the target information, and if so, store the target entity as a keyword into the target keyword set. In addition, the execution subject may also perform entity segmentation on the target information to obtain a plurality of entities, and if the obtained entities are target entities, store the entities as keywords in the target keyword set.
As an embodiment of the present application, the tag generating unit 403 is specifically configured to: and when the attribute information of the keywords comprises the keywords, aiming at each keyword in the target keyword set, comparing the corresponding keyword with a preset keyword set, and if the corresponding keyword belongs to the preset keyword set, determining the corresponding keyword as an enterprise tag of the target enterprise.
Here, for each keyword in the target keyword set, the executing entity may compare the keyword with a preset keyword set to determine whether the keyword belongs to the preset keyword set, and if so, take the keyword as an enterprise tag.
As an embodiment of the present application, the tag generating unit 403 is further specifically configured to: firstly, when the attribute information of the keywords comprises the semantic information of the keywords and the occurrence times of the keywords, aiming at each keyword in a target keyword set, a plurality of keywords with similar semantics with the corresponding keywords are selected from the target keyword set. Then, based on the occurrence frequency of each selected keyword in the target keyword set, selecting partial keywords meeting preset screening conditions from the multiple keywords, and generating enterprise tags of the target enterprises according to the selected partial keywords.
Here, for each keyword in the target keyword set, the execution subject may select a plurality of keywords having the same or similar semantics as the keyword from the target keyword set. Then, the execution subject may perform secondary selection from the plurality of keywords obtained by the primary selection according to the occurrence frequency of each keyword, thereby obtaining fewer and more accurate keywords. In this way, a smaller number of keywords can be analyzed, which helps to reduce the data processing volume.
The executive body may then use the resulting partial keywords to generate a business label for the target business. For example, the type corresponding to each keyword may be used as an enterprise tag. And generating enterprise labels by combining the semantics of the keywords. For example, if the partial keywords include the following three keywords "dirty", "garbage collection and transportation is not timely", and "foul", at this time, the enterprise tag may be generated by combining the semantics of the keywords: "evaluation poor".
It should be noted that the enterprise tag of the target enterprise may be generated in one manner, or may be generated in a combination of manners. When the enterprise label of the target enterprise is generated through combination of multiple modes, the enterprise labels of multiple angles can be obtained, the obtained label information is richer, and the enterprise portrait can be more comprehensively and accurately depicted.
As an embodiment of the present application, the apparatus further comprises a first tag extending unit (not shown in the figure). Wherein the first tag extension unit is configured to: firstly, label clustering processing is carried out on enterprise labels of target enterprises to obtain a plurality of categories and enterprise labels under each category. And then, generating enterprise labels aiming at the corresponding classes according to the semantic information of the enterprise labels under the classes.
Here, the executing entity may perform tag clustering processing on all tags of the target enterprise to implement classification of enterprise tags into multiple categories. With multiple enterprise tags under each category. Then, for each category, the executing entity may generate an enterprise tag corresponding to the category based on semantic information of each enterprise tag in the category. For example, all enterprise tags under the category may be input into a pre-trained neural network model to obtain a total enterprise tag for all enterprise tags under the category.
It should be noted that, since there may be common expressions of meanings of a plurality of enterprise tags, for example, the following three enterprise tags "garbage collection and transportation capability is strong", "garbage disposal method is advanced", and "garbage disposal speed is fast", the common expressions of the three tags are: the self-ability of the enterprise is stronger. Therefore, the executing agent may perform secondary tagging on the obtained enterprise tags, that is, perform clustering on all enterprise tags to obtain a plurality of categories, and generate a whole enterprise tag based on the attribute expressed by each category, for example, based on "garbage collection and transportation capability is strong", "garbage disposal method is advanced", "garbage disposal speed is fast", and "self capability of the enterprise is strong". Therefore, the generated enterprise label can be more accurate and richer. The method is favorable for better describing and depicting the enterprise portrait of the target enterprise.
As an embodiment of the present application, the apparatus further comprises a second tag expansion unit (not shown in the figure). Wherein the second tag extension unit is configured to: firstly, if the enterprise information comprises at least one piece of public sentiment information, carrying out word segmentation processing on the public sentiment information to obtain a plurality of segmentation words and the occurrence times of each segmentation word included in the public sentiment information, and inputting each segmentation word into a pre-trained binary classification model to obtain the emotional attribute of the corresponding segmentation word. Wherein the emotional attribute comprises a positive attribute and a negative attribute. Then, according to the emotional attribute and the occurrence frequency of each segmentation word included in the public opinion information, the emotional attribute of the public opinion information is determined. And finally, generating an enterprise label according to the emotional attribute of each public opinion information in the at least one public opinion information.
Here, the execution main body may perform a segmentation process on the public opinion information for each public opinion information, thereby obtaining a segmentation included in the public opinion information and the number of occurrences of the segmentation in the public opinion information. Then, for each segmented word, the executing body can input the segmented word into a binary model to obtain the emotion of the corresponding segmented word.
In practice, after obtaining the emotion attribute of each segment, a comprehensive value is usually calculated based on the emotion attribute of each segment and the corresponding weight of the emotion attribute, and the comprehensive value is used for indicating the emotion attribute of a piece of public opinion information.
Then, the executing entity may obtain the enterprise tag based on the emotional attributes of all the public sentiment information, for example, if there are 100 pieces of public sentiment information, 80 pieces of public sentiment information have negative emotional attributes, and 20 pieces of public sentiment information have positive emotional attributes, then the credit rating of the enterprise may not be high, and the enterprise tag may be generated as "low credibility".
According to the embodiment, richer and more accurate enterprise tags for the target enterprise can be obtained, and the enterprise portrait of the target enterprise can be better described and depicted, so that the accuracy of the generated enterprise portrait is further improved.
It should be understood that, in the structural block diagram of the enterprise representation generating apparatus shown in fig. 4, each unit is used to execute each step in the embodiment corresponding to fig. 1 to 3, and each step in the embodiment corresponding to fig. 1 to 3 has been explained in detail in the above embodiment, and please refer to the relevant description in the embodiments corresponding to fig. 1 to 3 and fig. 1 to 3 specifically, which is not described herein again.
Fig. 5 is a block diagram of a server according to another embodiment of the present application. As shown in fig. 5, the server 500 of this embodiment includes: a processor 501, a memory 502, and a computer program 503, such as a program for an enterprise representation generation method, stored in the memory 502 and executable on the processor 501. The processor 501, when executing the computer program 503, implements the steps of the above-described embodiments of the enterprise representation generation method, such as the steps 101 to 104 shown in fig. 1. Alternatively, when the processor 501 executes the computer program 503, the functions of the units in the embodiment corresponding to fig. 4, for example, the functions of the units 401 to 404 shown in fig. 4, are implemented, for which reference is specifically made to the relevant description in the embodiment corresponding to fig. 4, which is not repeated herein.
Illustratively, the computer program 503 may be divided into one or more units, which are stored in the memory 502 and executed by the processor 501 to accomplish the present application. One or more elements may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of computer program 503 in server 500. For example, the computer program 503 may be divided into an information acquisition unit, an information extraction unit, a label generation unit, and a portrait generation unit, each of which functions as described above.
The server may include, but is not limited to, a processor 501, a memory 502. Those skilled in the art will appreciate that fig. 5 is merely an example of a server 500, and does not constitute a limitation on server 500, and may include more or fewer components than shown, or some components in combination, or different components, e.g., a turntable device may also include input output devices, network access devices, buses, etc.
The Processor 501 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 502 may be an internal storage unit of the server 500, such as a hard disk or a memory of the server 500. The memory 502 may also be an external storage device of the server 500, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the server 500. Further, memory 502 may also include both internal storage units of server 500 and external storage devices. The memory 502 is used for storing computer programs and other programs and data required by the turntable device. The memory 502 may also be used to temporarily store data that has been output or is to be output.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated module, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. The computer readable storage medium may be non-volatile or volatile. Based on such understanding, all or part of the flow in the method of the embodiments described above can be realized by a computer program, which can be stored in a computer readable storage medium and can realize the steps of the embodiments of the methods described above when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. It should be noted that the computer readable storage medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable storage media that does not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. An enterprise representation generation method, the method comprising:
acquiring enterprise information of a target enterprise, and performing data preprocessing on the enterprise information to obtain the target information, wherein the data preprocessing comprises at least one of the following steps: data cleaning, data aggregation, data deletion and data conversion;
extracting keywords from the target information to obtain a target keyword set aiming at the target information;
generating an enterprise tag of the target enterprise based on the target keyword set and attribute information of each keyword in the target keyword set, wherein the attribute information of the keyword comprises at least one of the following items: the keywords themselves, semantic information of the keywords, and the occurrence times of the keywords;
and generating an enterprise portrait of the target enterprise according to the enterprise tags of the target enterprise.
2. The method for generating an enterprise representation as claimed in claim 1, wherein said extracting keywords from said target information to obtain a target keyword set for said target information comprises:
inputting the target information into a pre-trained keyword extraction model to obtain keywords included in the target information, and storing the obtained keywords into the target keyword set.
3. The method for generating an enterprise representation as claimed in claim 1, wherein said extracting keywords from said target information to obtain a target keyword set for said target information comprises:
and extracting a target entity from the target information to obtain the target entity included in the target information, and storing the extracted target entity as a keyword into the target keyword set.
4. The method for generating an enterprise representation as claimed in claim 1, wherein the generating of the enterprise tag of the target enterprise based on the target keyword set and the attribute information of each keyword in the target keyword set comprises:
and when the attribute information of the keywords comprises the keywords, aiming at each keyword in the target keyword set, comparing the corresponding keyword with a preset keyword set, and if the corresponding keyword belongs to the preset keyword set, determining the corresponding keyword as an enterprise tag of the target enterprise.
5. The method for generating an enterprise representation as claimed in claim 1, wherein the generating of the enterprise tag of the target enterprise based on the target keyword set and the attribute information of each keyword in the target keyword set comprises:
when the attribute information of the keywords comprises the semantic information of the keywords and the occurrence times of the keywords, aiming at each keyword in the target keyword set, selecting a plurality of keywords with similar semantics with the corresponding keywords from the target keyword set;
and selecting partial keywords meeting preset screening conditions from the plurality of keywords based on the occurrence frequency of each selected keyword in the target keyword set, and generating enterprise tags of the target enterprises according to the selected partial keywords.
6. An enterprise representation generation method according to claim 1, further comprising:
performing label clustering processing on the enterprise labels of the target enterprises to obtain a plurality of categories and enterprise labels under each category;
and generating enterprise labels aiming at the corresponding categories according to the semantic information of the enterprise labels under the categories.
7. An enterprise representation generation method according to any of claims 1-6 and also comprising:
if the enterprise information comprises at least one piece of public sentiment information, carrying out word segmentation processing on the public sentiment information to obtain a plurality of segmentation words and the occurrence times of each segmentation word included in the public sentiment information, and inputting each segmentation word into a pre-trained binary classification model to obtain the emotional attribute of the corresponding segmentation word, wherein the emotional attribute comprises a positive attribute and a negative attribute;
determining the emotional attribute of the public opinion information according to the emotional attribute and the occurrence frequency of each segmentation word included in the public opinion information;
and generating an enterprise label according to the emotional attribute of each public opinion information in the at least one public opinion information.
8. An enterprise representation generation apparatus, comprising:
the system comprises an information acquisition unit, a data preprocessing unit and a data processing unit, wherein the information acquisition unit is used for acquiring enterprise information of a target enterprise and carrying out data preprocessing on the enterprise information to obtain the target information, and the data preprocessing comprises at least one of the following steps: data cleaning, data aggregation, data deletion and data conversion;
the information extraction unit is used for extracting keywords from the target information to obtain a target keyword set aiming at the target information;
a tag generating unit, configured to generate an enterprise tag of the target enterprise based on the target keyword set and attribute information of each keyword in the target keyword set, where the attribute information of the keyword includes at least one of the following: the keywords themselves, semantic information of the keywords, and the occurrence times of the keywords;
and the portrait generation unit is used for generating enterprise portrayal of the target enterprise according to the enterprise tags of the target enterprise.
9. A server comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 7 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210059097.8A CN114398473A (en) | 2022-01-19 | 2022-01-19 | Enterprise portrait generation method, device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210059097.8A CN114398473A (en) | 2022-01-19 | 2022-01-19 | Enterprise portrait generation method, device, server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114398473A true CN114398473A (en) | 2022-04-26 |
Family
ID=81231665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210059097.8A Pending CN114398473A (en) | 2022-01-19 | 2022-01-19 | Enterprise portrait generation method, device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114398473A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115564486A (en) * | 2022-10-12 | 2023-01-03 | 企知道网络技术有限公司 | Data pushing method, device, equipment and medium |
| CN115599965A (en) * | 2022-12-13 | 2023-01-13 | 山东中慧强企信息科技有限公司（Cn） | Data economic informatization management system |
| CN116483881A (en) * | 2023-04-26 | 2023-07-25 | 北京远舢智能科技有限公司 | Data sampling method, device, electronic equipment and medium based on pull Ding Chao cube |
| CN116780536A (en) * | 2023-08-23 | 2023-09-19 | 山东未来互联科技有限公司 | Energy consumption prediction method and system based on machine learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105824898A (en) * | 2016-03-14 | 2016-08-03 | 苏州大学 | Label extracting method and device for network comments |
| CN106951409A (en) * | 2017-03-17 | 2017-07-14 | 黄淮学院 | A kind of network social intercourse media viewpoint tendency analysis system and method |
| CN108829672A (en) * | 2018-06-05 | 2018-11-16 | 平安科技（深圳）有限公司 | Sentiment analysis method, apparatus, computer equipment and the storage medium of text |
| CN112580332A (en) * | 2020-11-19 | 2021-03-30 | 淮阴工学院 | Enterprise portrait method based on label layering and deepening modeling |
-
2022
- 2022-01-19 CN CN202210059097.8A patent/CN114398473A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105824898A (en) * | 2016-03-14 | 2016-08-03 | 苏州大学 | Label extracting method and device for network comments |
| CN106951409A (en) * | 2017-03-17 | 2017-07-14 | 黄淮学院 | A kind of network social intercourse media viewpoint tendency analysis system and method |
| CN108829672A (en) * | 2018-06-05 | 2018-11-16 | 平安科技（深圳）有限公司 | Sentiment analysis method, apparatus, computer equipment and the storage medium of text |
| CN112580332A (en) * | 2020-11-19 | 2021-03-30 | 淮阴工学院 | Enterprise portrait method based on label layering and deepening modeling |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115564486A (en) * | 2022-10-12 | 2023-01-03 | 企知道网络技术有限公司 | Data pushing method, device, equipment and medium |
| CN115599965A (en) * | 2022-12-13 | 2023-01-13 | 山东中慧强企信息科技有限公司（Cn） | Data economic informatization management system |
| CN115599965B (en) * | 2022-12-13 | 2023-08-11 | 山东中慧强企信息科技有限公司 | Data economy informatization management system |
| CN116483881A (en) * | 2023-04-26 | 2023-07-25 | 北京远舢智能科技有限公司 | Data sampling method, device, electronic equipment and medium based on pull Ding Chao cube |
| CN116483881B (en) * | 2023-04-26 | 2024-05-03 | 北京远舢智能科技有限公司 | Data sampling method and device based on pull Ding Chao cube, electronic equipment and medium |
| CN116780536A (en) * | 2023-08-23 | 2023-09-19 | 山东未来互联科技有限公司 | Energy consumption prediction method and system based on machine learning |
| CN116780536B (en) * | 2023-08-23 | 2024-02-02 | 山东未来互联科技有限公司 | Energy consumption prediction method and system based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| CN109885773B (en) | Personalized article recommendation method, system, medium and equipment | |
| Hammad et al. | An approach for detecting spam in Arabic opinion reviews | |
| CN111767403B (en) | Text classification method and device | |
| CN114238573B (en) | Text countercheck sample-based information pushing method and device | |
| CN114398473A (en) | Enterprise portrait generation method, device, server and storage medium | |
| CN110909725A (en) | Method, device and equipment for recognizing text and storage medium | |
| CN111368042A (en) | Intelligent question and answer method and device, computer equipment and computer storage medium | |
| CN111767716B (en) | Method and device for determining enterprise multi-level industry information and computer equipment | |
| US20170329782A1 (en) | Query result bottom retrieval method and apparatus | |
| CN112330455B (en) | Method, device, equipment and storage medium for pushing information | |
| CN112035599B (en) | Query method and device based on vertical search, computer equipment and storage medium | |
| US20180046721A1 (en) | Systems and Methods for Automatic Customization of Content Filtering | |
| CN110909120B (en) | Resume searching/delivering method, device and system and electronic equipment | |
| CN101305368A (en) | Semantic visual search engine | |
| US20190130030A1 (en) | Generation method, generation device, and recording medium | |
| CN111538903B (en) | Method and device for determining search recommended word, electronic equipment and computer readable medium | |
| CN111797247B (en) | Case pushing method and device based on artificial intelligence, electronic equipment and medium | |
| CN117520503A (en) | Financial customer service dialogue generation method, device, equipment and medium based on LLM model | |
| CN115495636A (en) | Webpage searching method, device and storage medium | |
| CN116049376B (en) | Method, device and system for retrieving and replying information and creating knowledge | |
| Huang et al. | Tag refinement of micro-videos by learning from multiple data sources | |
| KR20230140849A (en) | Apparatus and method for video content recommendation | |
| CN113434649A (en) | Question matching method, device, equipment and medium based on policy FAQ database | |
| CN112528021A (en) | Model training method, model training device and intelligent equipment |
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 |