CN113434678A - Item reminding method, item reminding device, item reminding equipment and storage medium based on item types - Google Patents
Item reminding method, item reminding device, item reminding equipment and storage medium based on item types Download PDFInfo
- Publication number
- CN113434678A CN113434678A CN202110719423.9A CN202110719423A CN113434678A CN 113434678 A CN113434678 A CN 113434678A CN 202110719423 A CN202110719423 A CN 202110719423A CN 113434678 A CN113434678 A CN 113434678A
- Authority
- CN
- China
- Prior art keywords
- item
- reminded
- node
- reminding
- semantics
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004458 analytical method Methods 0.000 claims description 24
- 230000011218 segmentation Effects 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000011176 pooling Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 17
- 238000004891 communication Methods 0.000 description 7
- 230000004913 activation Effects 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06F16/35—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
- G06F16/33—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
- G06F16/338—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a data display technology, and discloses a matter reminding method based on matter types, which comprises the following steps: acquiring a to-be-reminded item of a user, extracting a keyword of the to-be-reminded item when the to-be-reminded item is a finished item, searching a related item according to the keyword, and reminding the user of the item by using the keyword and the related item; when the to-be-reminded item is not the completed item, identifying a plurality of item nodes of the to-be-reminded item; calculating the priority of the item nodes, and arranging a plurality of item nodes into a node sequence according to the sequence of the priority from big to small; and inquiring the item solution corresponding to each node semantic and filling the item solution into the node sequence, and reminding items to the user according to the sequence of the node sequence. In addition, the invention also relates to a block chain technology, and the to-be-reminded item can be stored in the node of the block chain. The invention also provides a device, equipment and a medium for reminding the events based on the event types. The invention can improve the refinement degree of the content when the item reminding is carried out.
Description
Technical Field
The present invention relates to the field of data display technologies, and in particular, to a method and an apparatus for item reminding based on item types, an electronic device, and a computer-readable storage medium.
Background
The matters needing to be processed in daily life of people are often trivial and fussy, so that people often leave out or do not process the matters in time when processing various matters, and therefore, in order to reduce the omission of the matters, people use memorandum, alarm clock reminding and other means to remind people of the matters to be processed more and more commonly.
In the existing item reminding, reminding based on a preset speech technology template is often performed, namely, when the item reminding is performed on a user, the user is reminded according to the preset speech technology template.
Disclosure of Invention
The invention provides a method and a device for item reminding based on item types and a computer readable storage medium, and mainly aims to solve the problem that the content is low in refinement degree when the item reminding is carried out.
In order to achieve the above object, the invention provides a method for reminding events based on event types, comprising:
acquiring a to-be-reminded item of a user, extracting item semantics of the to-be-reminded item, and judging whether the to-be-reminded item is a finished item or not according to the item semantics;
when the item type is the finished item, extracting an item key word of the item to be reminded, searching a preset associated item table according to the item key word to obtain the associated item of the item to be reminded, and reminding the item of the user by using the item key word and the associated item;
identifying a plurality of event nodes of the to-be-reminded event when the event type is not a completed event;
respectively calculating the priority of each item node, and arranging the item nodes into a node sequence according to the descending order of the priority;
extracting node semantics of each item node, and inquiring item solutions corresponding to each node semantics from a preset scheme library according to the node semantics;
and filling the item solution into the node sequence, and reminding items to the user according to the sequence of the node sequence.
Optionally, the extracting item semantics of the to-be-reminded item includes:
performing convolution and pooling on the to-be-reminded item by using a preset semantic analysis model to obtain a plurality of item features of the to-be-reminded item;
and respectively calculating the output value of each item feature in the item features, and selecting the item feature of which the output value is greater than a preset threshold value as the item semantic meaning of the item to be reminded.
Optionally, the determining whether the to-be-reminded item is a completed item according to the item semantics includes:
performing vector conversion on the item semantics to obtain a semantic vector;
calculating the distance value between the semantic vector and the semantic vector corresponding to the preset finished item;
if the distance value is larger than or equal to a preset distance threshold value, determining that the item to be reminded corresponding to the item semantics is not a finished item;
and if the distance value is smaller than a preset distance threshold value, determining that the item to be reminded corresponding to the item semantics is a finished item.
Optionally, the extracting the item keyword of the item to be reminded includes:
deleting the nonsense words of the items to be reminded to obtain standard item contents;
performing word segmentation processing on the standard item content by using a preset standard word bank to obtain item words;
counting the word segmentation frequency of each word in the item word segmentation and the position information of each word in the standard item content;
calculating the characteristic value of each participle in the event participle according to the participle frequency and the position information, and collecting the participle with the characteristic value larger than a preset characteristic threshold value in the event participle as the event keyword of the event to be reminded.
Optionally, the performing item reminding on the user by using the item keyword and the associated item includes:
performing syntactic structure analysis on the item keywords to obtain an analysis result;
performing syntactic structure completion on the item keywords according to the analysis result to obtain a reminding statement;
and taking the reminding statement and the associated matters as reminding contents to remind the user of the matters.
Optionally, the identifying the plurality of event nodes of the to-be-reminded event includes:
carrying out paragraph splitting on the to-be-reminded item to obtain a split paragraph;
extracting paragraph keywords of each split paragraph;
carrying out vector transformation on the paragraph key words of each split paragraph to obtain a paragraph key word vector;
respectively calculating a matching value of each paragraph keyword vector and a preset standard item node;
and determining the item node corresponding to the splitting paragraph according to the matching value.
Optionally, the populating the transaction solution to the sequence of nodes includes:
selecting one item node from the node sequence one by one as a target node;
calculating the executable degree of the item solution corresponding to the target node;
arranging the item solutions into a scheme table according to the sequence of the executability from large to small;
and writing the scheme table into the target node.
In order to solve the above problem, the present invention further provides an item reminder apparatus based on an item type, the apparatus including:
the semantic extraction module is used for acquiring the to-be-reminded items of the user, extracting item semantics of the to-be-reminded items and judging whether the to-be-reminded items are finished items or not according to the item semantics;
the first reminding module is used for extracting the item key words of the items to be reminded when the item type is the finished item, retrieving the associated items of the items to be reminded from a preset associated item table according to the item key words, and reminding the user of the items by using the item key words and the associated items;
the node identification module is used for identifying a plurality of item nodes of the item to be reminded when the item type is not the finished item;
the node sorting module is used for respectively calculating the priority of each item node and sorting the item nodes into a node sequence according to the descending order of the priority;
the scheme query module is used for extracting the node semantics of each item node and querying an item solution corresponding to each node semantics from a preset scheme library according to the node semantics;
and the second reminding module is used for filling the item solution into the node sequence and reminding the user of the item according to the sequence of the node sequence.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one instruction; and
and the processor executes the instructions stored in the memory to realize the item reminding method based on the item type.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, which stores at least one instruction, where the at least one instruction is executed by a processor in an electronic device to implement the item reminding method based on item type.
The embodiment of the invention can classify the items to be reminded, when the items to be reminded are finished items, the associated items associated with the items to be reminded are inquired, the items to be reminded are reminded for the user by using the content of the items to be reminded and the content of the associated items, when the items to be reminded are not finished items, a solution for finishing the items to be reminded is given, and the items are reminded for the user by using the solution, so that the refinement degree of the content when the items are reminded for the user is improved. Therefore, the item reminding method, the item reminding device, the electronic equipment and the computer readable storage medium based on the item types can solve the problem that the content is low in refinement degree when the item reminding is carried out.
Drawings
FIG. 1 is a flowchart illustrating a method for reminding an event based on event type according to an embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating a process of determining whether a to-be-reminded item is a completed item according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart illustrating item reminders for users by using item keywords and associated items according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of an event reminder device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device for implementing the item reminding method based on item types according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides a matter reminding method based on matter types. The execution subject of the item reminding method based on the item type includes, but is not limited to, at least one of the electronic devices that can be configured to execute the method provided by the embodiment of the present application, such as a server, a terminal, and the like. In other words, the item reminding method based on the item type may be executed by software or hardware installed in the terminal device or the server device, and the software may be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Fig. 1 is a schematic flow chart of an event reminding method based on event types according to an embodiment of the present invention. In this embodiment, the item reminding method based on the item type includes:
s1, obtaining the items to be reminded of the user, and extracting the item semantics of the items to be reminded.
In the embodiment of the present invention, the items to be reminded include items that the user wants to be reminded, for example, credit card repayment reminding items, trip reminding items, financial product expiration reminding items, and the like.
In the embodiment of the invention, the pre-stored to-be-reminded item can be grabbed from a predetermined storage area through a computer sentence (java sentence, python sentence, etc.) with a data grabbing function, wherein the storage area includes but is not limited to a database, a block chain node, a network cache, etc.
Alternatively, the to-be-reminded items uploaded by the user at the user end (mobile phone, personal computer, tablet, etc.) may be obtained, such as the schedule filled in by the user in the calendar of the mobile phone, the business trip plan filled in the memo of the personal computer by the user, and the like.
In the embodiment of the invention, the item to be reminded can be analyzed by utilizing a pre-trained semantic analysis model so as to extract the item semantics of the item to be reminded, wherein the item semantics refers to semantic information capable of representing the key content of the item to be reminded.
In detail, the semantic analysis model includes: models having a text semantic analysis function, such as NLP (Natural Language Processing) models and HMMs (Hidden Markov models).
In the implementation of the present invention, the extracting item semantics of the to-be-reminded item includes:
performing convolution and pooling on the to-be-reminded item by using a preset semantic analysis model to obtain a plurality of item features of the to-be-reminded item;
and respectively calculating the output value of each item feature in the item features, and selecting the item feature of which the output value is greater than a preset threshold value as the item semantic meaning of the item to be reminded.
In detail, the semantic analysis model can be used for performing convolution and pooling on the item to be reminded so as to screen out a plurality of item features of the item to be reminded, reduce the data volume to be analyzed and further be beneficial to improving the accuracy of extracted item semantics.
Further, the item features screened out through operations such as convolution, pooling and the like may not be accurate enough and include some item features that cannot be used for expressing the key content of the item to be reminded, so that a preset activation function may be used to calculate an output value of each of the item features, and the item feature having the output value greater than a preset output threshold is selected as the item semantics of the item to be reminded.
In detail, the activation function includes, but is not limited to, a sigmoid activation function, a softmax activation function, a Relu activation function.
S2, judging whether the item to be reminded is a finished item according to the item semantic.
In one practical application scenario of the invention, the reminding modes are different due to different types of matters.
Therefore, the embodiment of the invention can judge the item type of the item to be reminded according to the item semantics of the item to be reminded, which is beneficial to accurately reminding the user of the item according to different item types in the following, wherein the item types comprise finished items and non-finished items.
For example, the user does not need to execute any operation flow, such as the financial product due reminder item and the insurance due reminder item, and the like, and the items can be automatically completed after reaching the preset time limit, and the items can be confirmed to be completed items, that is, the items can be automatically completed when reaching the preset time limit.
Or, after the user plans the business trip reminding item and the user attendance activity reminding item to remind the user, the user needs to perform related operations (for example, selecting a trip mode, a business trip route and the like during business trip) after the item is finished, and it can be confirmed that the item is not the finished item, that is, when the preset time limit is reached, the item cannot be automatically finished. .
In the embodiment of the present invention, referring to fig. 2, the determining whether the to-be-reminded item is a completed item according to the item semantic includes:
s21, performing vector conversion on the item semantics to obtain a semantic vector;
s22, calculating the distance value between the semantic vector and the semantic vector corresponding to the preset completed item;
s23, judging whether the distance value is smaller than a preset distance threshold value;
if the distance value is greater than or equal to a preset distance threshold, executing S24, and determining that the item to be reminded corresponding to the item semantic is not a completed item;
if the distance value is smaller than the preset distance threshold, executing S25, and determining that the to-be-reminded item corresponding to the item semantic is a completed item.
In detail, the event semantics can be vector-converted by using a vector model with a vector conversion function, so as to obtain a semantic vector, wherein the vector model includes, but is not limited to, a word2vec model and a bert model.
Specifically, the calculating a distance value between the semantic vector and a semantic vector corresponding to a preset completed event includes:
calculating the distance value of the semantic vector corresponding to the semantic vector and the preset completed item by using the following distance algorithm:
wherein D is the distance value, a is the semantic vector, and b is the semantic vector corresponding to the preset completed item.
When the item type is the completed item, S3 is executed, the item keyword of the item to be reminded is extracted, the associated item of the item to be reminded is retrieved from a preset associated item table according to the item keyword, and the item keyword and the associated item are used to remind the user of the item.
In the embodiment of the present invention, when the type of the event is a completed event, for example, the to-be-reminded event is: when the financial product A purchased by the user is due, the user needs to be reminded; the user can be reminded of the items (the purchase reminding of the financial product B and the financial product C) related to the financial product A, and the content of the item reminding of the expiration of the financial product A is enriched.
In detail, the item keywords of the item to be reminded can be extracted, the associated item associated with the item to be reminded can be retrieved from a preset associated item table according to the item keywords, and then the reminder content is generated by using the keywords and the associated item to remind the user of the item, the associated item table can be preset by the user, and the associated item table comprises a plurality of items and associated items corresponding to each item.
In the embodiment of the present invention, the extracting the item keyword of the item to be reminded includes:
deleting the nonsense words of the items to be reminded to obtain standard item contents;
performing word segmentation processing on the standard item content by using a preset standard word bank to obtain item words;
counting the word segmentation frequency of each word in the item word segmentation and the position information of each word in the standard item content;
calculating the characteristic value of each participle in the event participle according to the participle frequency and the position information, and collecting the participle with the characteristic value larger than a preset characteristic threshold value in the event participle as the event keyword of the event to be reminded.
Specifically, the nonsense word refers to a nonsense word in the to-be-reminded item, such as: and performing nonsense word deletion on the items to be reminded, so that the data volume needing to be processed subsequently can be reduced, words irrelevant to the actual semantics in the items to be reminded are removed, and the efficiency and the accuracy of performing key words on the items to be reminded subsequently are improved.
In detail, the position information refers to a sequence of positions of the item segmentation in the standard item content, for example, the standard item content is: and if the item participle A is the item participle B, the item participle A is at the most front position in the standard item content, the item participle B is at the middle position in the standard item content, and the item participle C is at the most rear position in the standard item content.
In one practical application scenario of the present invention, the more front words can be considered, the greater the importance of the words is, the more frequent words are, the greater the importance of the words is, therefore, the word segmentation frequency of each word in the event word segmentation and the position information of each word in the standard event content can be counted, and the importance of each event word can be determined according to the word segmentation frequency and the position information.
In the embodiment of the present invention, a preset key value algorithm may be used to calculate a feature value of each of the item segmentations, where the key value algorithm includes, but is not limited to: TF-IDF algorithm, PageRank algorithm and textRank algorithm.
In one embodiment of the present invention, the calculating a feature value of each of the event segmentations according to the segmentation frequency and the location information includes:
calculating the characteristic value of each participle in the item participle by using the following characteristic value algorithm:
T=α*A+β*B
wherein T is the key value, A is the word segmentation frequency, B is the numerical expression of the position information, and alpha and beta are preset weight coefficients.
Further, in the embodiment of the present invention, an INDEX of the related item table may be created by using a CREATE INDEX function in an SQL library, and then the related item of the item to be reminded is obtained by retrieving in the related item table according to the item keyword and the INDEX.
After the item keywords and the associated items are obtained, the embodiment of the invention takes the item keywords and the associated items extracted from the items to be reminded as reminding contents to remind the user of the items.
For example, the item keyword and the related item are used as the content of the item reminder, and the user is reminded in a manner of a prompt box, a short message and the like.
In the embodiment of the invention, because the keyword is one or more words extracted from the item segmentation of the item to be reminded, and there may be a case that the sentence structure is incomplete, if the keyword is directly used as the reminding content to remind the user of the item, the semantics in the content of the item reminding is not accurate, and the accuracy of the item reminding for the user is further reduced.
In an embodiment of the present invention, referring to fig. 3, the performing item reminding on the user by using the item keyword and the associated item includes:
s31, carrying out syntactic structure analysis on the item keywords to obtain an analysis result;
s32, performing syntactic structure completion on the item keywords according to the analysis result to obtain a reminding statement;
and S33, taking the reminding sentence and the associated matters as reminding contents, and reminding the user of matters.
Specifically, the syntactic structure refers to sentence structures such as a subject, a predicate, and an object in a sentence, and the event keyword can be analyzed by using a pre-constructed syntactic structure analysis model with a syntactic structure analysis function to obtain an analysis result of which part of the sentence structure is missing in the event keyword, and then the syntactic structure of the event keyword is supplemented according to the analysis result in a targeted manner to obtain a reminder sentence with a complete syntactic structure.
Specifically, the syntactic structure analysis model includes, but is not limited to, a BERT model, an LSTM model.
For example, the item keyword is a credit card or a repayment, so that the item keyword can be analyzed by the syntactic structure analysis model to obtain an analysis result that the item keyword lacks a subject and a shape, and further, the item keyword is subjected to syntactic structure completion according to the analysis result to obtain a reminder sentence: the user pays a credit card in xx month xx, wherein the user is a supplemented subject, and the user is a supplemented subject in xx month xx.
In the embodiment of the invention, the sentence structure completion is carried out on the item keywords, so that the precision and the understandability of the reminding content can be improved when the item reminding is carried out on the user.
When the event type is not a completed event, S4 is executed, identifying a plurality of event nodes of the to-be-reminded event.
In the embodiment of the present invention, when the type of the event is not a completed event, for example, the to-be-reminded event is: the user plans to go out of city A; when the user is reminded of the events, a solution to the to-be-reminded events can be given so as to realize accurate reminding of the user.
In one practical application scenario of the present invention, since the to-be-reminded item may include a plurality of item nodes, for example, when the to-be-reminded item is: when the user plans to go to city a for business, the reminder may include: the method comprises the steps of selecting a travel tool, taking the travel tool to arrive at a city A, ordering a lodging and other item nodes, so that in order to realize accurate item reminding for a user, the item to be reminded can be subjected to node identification, and the subsequent item reminding can be performed according to different item nodes.
In an embodiment of the present invention, the identifying the plurality of event nodes of the to-be-reminded event includes:
carrying out paragraph splitting on the to-be-reminded item to obtain a split paragraph;
extracting paragraph keywords of each split paragraph;
carrying out vector transformation on the paragraph key words of each split paragraph to obtain a paragraph key word vector;
respectively calculating a matching value of each paragraph keyword vector and a preset standard item node;
and determining the item node corresponding to the splitting paragraph according to the matching value.
In detail, the paragraph splitting the to-be-reminded item to obtain a split paragraph includes:
determining a segmenter location in the transaction text by traversing the transaction text;
and carrying out paragraph splitting on the item text according to the position of the segmentation character to obtain a plurality of text paragraphs.
In particular, the segmenter is a predetermined symbol that may be used for segmentation of text content paragraphs, e.g., "§ cAnd the like.
For example, if there is a to-be-reminded item "go to airport at 3 pm on a small red day, go to beijing and go on business after arriving at the airport, … …", where the segmentation symbol is ",", the to-be-reminded item may be split into text paragraphs 1: "exit to airport at 3 pm on the small red day", text paragraph 2: "get to the airport and take the plane to get out of business in Beijing".
Specifically, the step of extracting the paragraph keyword of each of the split paragraphs is consistent with the step of extracting the item keyword of the item to be reminded in S2, and details thereof are not repeated herein.
In this embodiment of the present invention, the step of performing vector transformation on the paragraph keyword of each of the split paragraphs is the same as the step of performing vector transformation on the item semantics in S1, and details are not repeated here.
In detail, the calculating a matching value between each paragraph keyword vector and a preset standard item node includes:
respectively calculating the matching value of each paragraph keyword vector and a preset standard item node by using the following matching value algorithm:
wherein P is the matching value, xiIs the i-th paragraph keyword vector, yjAnd theta is a preset constant coefficient for the jth preset standard matter node.
In the embodiment of the present invention, the transaction node corresponding to the split paragraph may be determined according to the matching value.
For example, if there is a feature vector P, the matching degree between the feature vector P and the criterion item node a is 20, the matching degree between the feature vector P and the criterion item node b is 50, and the matching degree between the feature vector P and the criterion item node c is 80, the item node of the paragraph feature word corresponding to the feature vector is determined to be the criterion item node c.
S5, calculating the priority of each transaction node, and arranging the transaction nodes into a node sequence according to the descending order of the priority.
In the embodiment of the present invention, because the plurality of event nodes of the to-be-reminded event need to be executed according to a fixed sequence, for example, the to-be-reminded event "go out to the airport at 3 pm in the morning and go out to beijing by taking an airplane after arriving at the airport" includes event node a: exit to airport at 3 pm on the day of the little Hongming, and item node B: after arriving at an airport, taking an airplane to go out of business in Beijing, a user needs to firstly carry out an item node A and then carry out an item node B; therefore, in order to more accurately remind the user of the event, the embodiment of the invention can calculate the priority of each event node and arrange the event nodes into the reception sequence according to the descending order of the priority.
In this embodiment of the present invention, the calculating the priority of each transaction node includes:
counting the paragraph position of the split paragraph corresponding to each item node in the item to be reminded, and the content ratio of the split paragraph corresponding to each item node in the item to be reminded;
and calculating the priority of each item node according to the ratio of the paragraph position to the content by using a preset weight algorithm.
In detail, the step of counting the paragraph positions of the split paragraphs corresponding to each item node in the to-be-reminded item is consistent with the step of counting the position information of each word in the standard item content in S2, and details are not repeated here.
Specifically, the content proportion refers to the proportion of the split paragraphs corresponding to the event node in the content of all the split paragraphs of the to-be-reminded event, and when the proportion of the split paragraphs corresponding to the event node in the content of all the split paragraphs of the to-be-reminded event is larger, the priority of the event node is higher.
In the embodiment of the invention, the weight algorithm is as follows:
where Pre is the priority, WnThe paragraph position of the split paragraph corresponding to the nth item node in the item to be reminded, BnThe content of the split paragraph corresponding to the nth item node in the item to be reminded is in proportion,and omega is a preset weight coefficient.
In the embodiment of the present invention, the plurality of transaction nodes are arranged into a node sequence according to the order of the priorities from large to small.
For example, there are a transaction node a, a transaction node B, and a transaction node C, where the priority of the transaction node a is 50, the priority of the transaction node B is 60, and the priority of the transaction node C is 80, so three transaction nodes can be arranged in a node sequence in descending order of the priorities: transaction node C, transaction node B, and transaction node A.
S6, extracting the node semantics of each item node, and inquiring an item solution corresponding to each node semantics from a preset solution library according to the node semantics.
In the embodiment of the present invention, since each event node is completed by a user, for example, a to-be-reminded event "go out to an airport at 3 pm on a small reddish day, and go out to beijing by taking an airplane after arriving at the airport" includes an event node a: exit to airport at 3 pm on the day of the little Hongming, and item node B: and taking an airplane to go to Beijing for business after arriving at the airport, wherein when the item node A is executed, the user is required to select which transportation means to take to go to the airport, and when the item node B is executed, the user is required to select which flight to take to get to Beijing.
Therefore, in order to make the content of the event reminding for the user more detailed, the embodiment of the present invention performs semantic extraction on each event node, and queries an event solution corresponding to the node semantic from a preset solution library according to the extracted node semantic, where the solution library may be a pre-constructed database, and the solution library stores the node semantics of a plurality of event nodes and a selectable solution corresponding to each node semantic.
In this embodiment of the present invention, the step of extracting the node semantics of each item node is the same as the step of extracting the item semantics of the to-be-reminded item in S1, and details thereof are not repeated here.
In the embodiment of the present invention, the step of querying the item solution corresponding to the node semantics from the preset solution library according to the node semantics is consistent with the step of retrieving the associated item of the item to be reminded from the preset associated item table according to the item keyword in S2, and details are not repeated here.
For example, when there is a transaction node A: when the user leaves the airport at 3 pm in the morning in the Ming Hongming day, the core semantic of the item node can be extracted to get the airport, and the core semantic is searched in the scheme library to obtain a scheme A: drop to airport on ride, scenario B: taking a net to reserve a car to an airport, scheme C: the vehicle is driven to the airport by itself.
And S7, filling the item solution into the node sequence, and reminding items to the user according to the sequence of the node sequence.
In the embodiment of the present invention, the queried item solutions may be filled into the node sequence, and further, an item reminder is performed to the user according to the sequence of the node sequence.
For example, the node sequence has a transaction node A and a transaction node B, wherein the transaction solution that queries the transaction node A includes solution a1Scheme a2And scheme a3The solution of the transaction node B comprises a scheme B1Scheme b2And scheme b3Thus, scheme a can be used1Scheme a2And scheme a3Filling the item node A of the node sequence with the scheme b1Scheme b2And scheme b3And filling the event node B into the node sequence, and further reminding the user of the event according to the sequence of the event node A and the event node B.
In an embodiment of the present invention, the populating the transaction solution into the node sequence includes:
selecting one item node from the node sequence one by one as a target node;
calculating the executable degree of the item solution corresponding to the target node;
arranging the item solutions into a scheme table according to the sequence of the executability from large to small;
and writing the scheme table into the target node.
In detail, the calculating the executable degree of the item solution corresponding to the target node includes:
calculating the executable degree of the item solution corresponding to the target node by using the following executable degree algorithm:
K=C-D*Ts-R*Ms
wherein K is the executable degree, C is a preset constant, TsFor executing the predicted elapsed time of the s-th transaction solution corresponding to the target node, MsD, R is a preset weighting factor for executing the predicted amount of money consumed for the s-th transaction solution corresponding to the target node.
Specifically, in the embodiment of the present invention, the transaction solutions are arranged into the solution table according to the sequence from the large executable degree to the small executable degree, for example, the transaction solutions corresponding to the target node include: a scheme a, a scheme b and a scheme c, wherein the executable degree of the scheme a is 33, the executable degree of the scheme b is 55, and the executable degree of the scheme c is 77, the transaction solutions corresponding to the target nodes can be arranged into a scheme table according to the sequence of the executable degrees from large to small: scheme c, scheme b and scheme a.
In the embodiment of the present invention, after the item solution is filled into the node sequence, the content of each item node in the node sequence may be pushed to the user according to the sequence of the node sequence, so as to implement item reminding for the user.
The embodiment of the invention can classify the items to be reminded, when the items to be reminded are finished items, the associated items associated with the items to be reminded are inquired, the items to be reminded are reminded for the user by using the content of the items to be reminded and the content of the associated items, when the items to be reminded are not finished items, a solution for finishing the items to be reminded is given, and the items are reminded for the user by using the solution, so that the refinement degree of the content when the items are reminded for the user is improved. Therefore, the item reminding method, the item reminding device, the electronic equipment and the computer readable storage medium based on the item types can solve the problem that the content is low in refinement degree when the item reminding is carried out.
Fig. 4 is a functional block diagram of an event reminder device according to an embodiment of the present invention.
The event reminder device 100 based on the event type according to the present invention can be installed in an electronic device. According to the implemented functions, the event reminder device 100 based on the event type may include a semantic extraction module 101, a first reminder module 102, a node identification module 103, a node sorting module 104, a scheme query module 105, and a second reminder module 106. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the semantic extraction module 101 is configured to obtain an item to be reminded of a user, extract item semantics of the item to be reminded, and determine whether the item to be reminded is a completed item according to the item semantics;
the first reminding module 102 is configured to, when the item type is a completed item, extract an item keyword of the item to be reminded, retrieve, according to the item keyword, an associated item of the item to be reminded from a preset associated item table, and remind the user of the item by using the item keyword and the associated item;
the node identification module 103 is configured to identify a plurality of event nodes of the to-be-reminded event when the event type is not a completed event;
the node sorting module 104 is configured to calculate a priority of each transaction node, and arrange the transaction nodes into a node sequence according to a descending order of the priorities;
the solution query module 105 is configured to extract a node semantic of each item node, and query an item solution corresponding to each node semantic from a preset solution library according to the node semantic;
the second reminding module 106 is configured to fill the item solution into the node sequence, and remind the user of the item according to the sequence of the node sequence.
In detail, when the event reminder device 100 based on the event type according to the embodiment of the present invention is used, the same technical means as the event reminder method based on the event type described in fig. 1 to fig. 3 is adopted, and the same technical effects can be produced, which is not described herein again.
Fig. 5 is a schematic structural diagram of an electronic device for implementing an item reminding method based on item types according to an embodiment of the present invention.
The electronic device 1 may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may further include a computer program, such as a transaction reminder based on the type of transaction, stored in the memory 11 and operable on the processor 10.
In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same function or different functions, and includes one or more Central Processing Units (CPUs), a microprocessor, a digital Processing chip, a graphics processor, a combination of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device by running or executing programs or modules (e.g., executing event reminder based on event types, etc.) stored in the memory 11 and calling data stored in the memory 11.
The memory 11 includes at least one type of readable storage medium including flash memory, removable hard disks, multimedia cards, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, for example a removable hard disk of the electronic device. The memory 11 may also be an external storage device of the electronic device in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only to store application software installed in the electronic device and various types of data, such as codes of event reminders based on event types, but also to temporarily store data that has been output or is to be output.
The communication bus 12 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
The communication interface 13 is used for communication between the electronic device and other devices, and includes a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable, among other things, for displaying information processed in the electronic device and for displaying a visualized user interface.
Fig. 5 only shows an electronic device with components, and it will be understood by a person skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management and the like are realized through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The transaction reminder stored in the memory 11 of the electronic device 1 based on the transaction type is a combination of instructions, which when executed in the processor 10, can implement:
acquiring a to-be-reminded item of a user, extracting item semantics of the to-be-reminded item, and judging whether the to-be-reminded item is a finished item or not according to the item semantics;
when the item type is the finished item, extracting an item key word of the item to be reminded, searching a preset associated item table according to the item key word to obtain the associated item of the item to be reminded, and reminding the item of the user by using the item key word and the associated item;
identifying a plurality of event nodes of the to-be-reminded event when the event type is not a completed event;
respectively calculating the priority of each item node, and arranging the item nodes into a node sequence according to the descending order of the priority;
extracting node semantics of each item node, and inquiring item solutions corresponding to each node semantics from a preset scheme library according to the node semantics;
and filling the item solution into the node sequence, and reminding items to the user according to the sequence of the node sequence.
Specifically, the specific implementation method of the processor 10 for the instruction may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:
acquiring a to-be-reminded item of a user, extracting item semantics of the to-be-reminded item, and judging whether the to-be-reminded item is a finished item or not according to the item semantics;
when the item type is the finished item, extracting an item key word of the item to be reminded, searching a preset associated item table according to the item key word to obtain the associated item of the item to be reminded, and reminding the item of the user by using the item key word and the associated item;
identifying a plurality of event nodes of the to-be-reminded event when the event type is not a completed event;
respectively calculating the priority of each item node, and arranging the item nodes into a node sequence according to the descending order of the priority;
extracting node semantics of each item node, and inquiring item solutions corresponding to each node semantics from a preset scheme library according to the node semantics;
and filling the item solution into the node sequence, and reminding items to the user according to the sequence of the node sequence.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention 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, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A method for item reminders based on item type, the method comprising:
acquiring a to-be-reminded item of a user, extracting item semantics of the to-be-reminded item, and judging whether the to-be-reminded item is a finished item or not according to the item semantics;
when the item type is the finished item, extracting an item key word of the item to be reminded, searching a preset associated item table according to the item key word to obtain the associated item of the item to be reminded, and reminding the item of the user by using the item key word and the associated item;
identifying a plurality of event nodes of the to-be-reminded event when the event type is not a completed event;
respectively calculating the priority of each item node, and arranging the item nodes into a node sequence according to the descending order of the priority;
extracting node semantics of each item node, and inquiring item solutions corresponding to each node semantics from a preset scheme library according to the node semantics;
and filling the item solution into the node sequence, and reminding items to the user according to the sequence of the node sequence.
2. The item reminding method based on item type as claimed in claim 1, wherein said extracting item semantics of said item to be reminded comprises:
performing convolution and pooling on the to-be-reminded item by using a preset semantic analysis model to obtain a plurality of item features of the to-be-reminded item;
and respectively calculating the output value of each item feature in the item features, and selecting the item feature of which the output value is greater than a preset threshold value as the item semantic meaning of the item to be reminded.
3. The item reminding method based on item type as claimed in claim 1, wherein said determining whether the item to be reminded is a completed item according to the item semantics comprises:
performing vector conversion on the item semantics to obtain a semantic vector;
calculating the distance value between the semantic vector and the semantic vector corresponding to the preset finished item;
if the distance value is larger than or equal to a preset distance threshold value, determining that the item to be reminded corresponding to the item semantics is not a finished item;
and if the distance value is smaller than a preset distance threshold value, determining that the item to be reminded corresponding to the item semantics is a finished item.
4. The item reminding method based on item type as claimed in claim 1, wherein said extracting the item keyword of the item to be reminded comprises:
deleting the nonsense words of the items to be reminded to obtain standard item contents;
performing word segmentation processing on the standard item content by using a preset standard word bank to obtain item words;
counting the word segmentation frequency of each word in the item word segmentation and the position information of each word in the standard item content;
calculating the characteristic value of each participle in the event participle according to the participle frequency and the position information, and collecting the participle with the characteristic value larger than a preset characteristic threshold value in the event participle as the event keyword of the event to be reminded.
5. The item reminding method based on item type as claimed in claim 1, wherein said reminding item to said user by said item keyword and said associated item comprises:
performing syntactic structure analysis on the item keywords to obtain an analysis result;
performing syntactic structure completion on the item keywords according to the analysis result to obtain a reminding statement;
and taking the reminding statement and the associated matters as reminding contents to remind the user of the matters.
6. The item reminder method according to any one of claims 1 to 5, wherein the identifying the plurality of item nodes of the item to be reminded includes:
carrying out paragraph splitting on the to-be-reminded item to obtain a split paragraph;
extracting paragraph keywords of each split paragraph;
carrying out vector transformation on the paragraph key words of each split paragraph to obtain a paragraph key word vector;
respectively calculating a matching value of each paragraph keyword vector and a preset standard item node;
and determining the item node corresponding to the splitting paragraph according to the matching value.
7. The item reminder method according to any one of claims 1 to 5, wherein the populating the item solution to the sequence of nodes includes:
selecting one item node from the node sequence one by one as a target node;
calculating the executable degree of the item solution corresponding to the target node;
arranging the item solutions into a scheme table according to the sequence of the executability from large to small;
and writing the scheme table into the target node.
8. An item reminder apparatus based on an item type, the apparatus comprising:
the semantic extraction module is used for acquiring the to-be-reminded items of the user, extracting item semantics of the to-be-reminded items and judging whether the to-be-reminded items are finished items or not according to the item semantics;
the first reminding module is used for extracting the item key words of the items to be reminded when the item type is the finished item, retrieving the associated items of the items to be reminded from a preset associated item table according to the item key words, and reminding the user of the items by using the item key words and the associated items;
the node identification module is used for identifying a plurality of item nodes of the item to be reminded when the item type is not the finished item;
the node sorting module is used for respectively calculating the priority of each item node and sorting the item nodes into a node sequence according to the descending order of the priority;
the scheme query module is used for extracting the node semantics of each item node and querying an item solution corresponding to each node semantics from a preset scheme library according to the node semantics;
and the second reminding module is used for filling the item solution into the node sequence and reminding the user of the item according to the sequence of the node sequence.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of event reminder based on an event type as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the item reminder method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110719423.9A CN113434678B (en) | 2021-06-28 | 2021-06-28 | Item type-based item reminding method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110719423.9A CN113434678B (en) | 2021-06-28 | 2021-06-28 | Item type-based item reminding method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113434678A true CN113434678A (en) | 2021-09-24 |
CN113434678B CN113434678B (en) | 2024-03-19 |
Family
ID=77754921
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110719423.9A Active CN113434678B (en) | 2021-06-28 | 2021-06-28 | Item type-based item reminding method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113434678B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115688759A (en) * | 2022-11-07 | 2023-02-03 | 北京北明数科信息技术有限公司 | Method, system, computer equipment and medium for classifying reported information |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104899724A (en) * | 2015-06-29 | 2015-09-09 | 北京金山安全软件有限公司 | Method and device for generating item reminding |
KR20180074567A (en) * | 2016-12-23 | 2018-07-03 | 삼성전자주식회사 | System and method for providing to-do-list of user |
CN109587037A (en) * | 2018-11-23 | 2019-04-05 | 北京奇安信科技有限公司 | The method and device of backlog is created in timely communication system |
CN109992601A (en) * | 2019-03-12 | 2019-07-09 | 中国平安财产保险股份有限公司 | Method for pushing, device and the computer equipment of backlog information |
CN110175806A (en) * | 2019-04-16 | 2019-08-27 | 平安科技(深圳)有限公司 | Item based reminding method, device and computer equipment based on semantic analysis |
CN112598377A (en) * | 2020-12-16 | 2021-04-02 | 长沙市到家悠享网络科技有限公司 | Item reminding method, system, device, equipment and storage medium |
-
2021
- 2021-06-28 CN CN202110719423.9A patent/CN113434678B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104899724A (en) * | 2015-06-29 | 2015-09-09 | 北京金山安全软件有限公司 | Method and device for generating item reminding |
KR20180074567A (en) * | 2016-12-23 | 2018-07-03 | 삼성전자주식회사 | System and method for providing to-do-list of user |
CN109587037A (en) * | 2018-11-23 | 2019-04-05 | 北京奇安信科技有限公司 | The method and device of backlog is created in timely communication system |
CN109992601A (en) * | 2019-03-12 | 2019-07-09 | 中国平安财产保险股份有限公司 | Method for pushing, device and the computer equipment of backlog information |
CN110175806A (en) * | 2019-04-16 | 2019-08-27 | 平安科技(深圳)有限公司 | Item based reminding method, device and computer equipment based on semantic analysis |
CN112598377A (en) * | 2020-12-16 | 2021-04-02 | 长沙市到家悠享网络科技有限公司 | Item reminding method, system, device, equipment and storage medium |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115688759A (en) * | 2022-11-07 | 2023-02-03 | 北京北明数科信息技术有限公司 | Method, system, computer equipment and medium for classifying reported information |
CN115688759B (en) * | 2022-11-07 | 2023-11-07 | 北京北明数科信息技术有限公司 | Method, system, computer equipment and medium for classifying reported information |
Also Published As
Publication number | Publication date |
---|---|
CN113434678B (en) | 2024-03-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022141861A1 (en) | Emotion classification method and apparatus, electronic device, and storage medium | |
CN104169950B (en) | Utilize the Database Systems of the calculating towards batch processing | |
US11354367B2 (en) | Search engine | |
US20160306800A1 (en) | Reply recommendation apparatus and system and method for text construction | |
CN103548019A (en) | Method and system for providing statistical from a data warehouse | |
CN113449187A (en) | Product recommendation method, device and equipment based on double portraits and storage medium | |
CN112883190A (en) | Text classification method and device, electronic equipment and storage medium | |
CN105426514A (en) | Personalized mobile APP recommendation method | |
CN112380859A (en) | Public opinion information recommendation method and device, electronic equipment and computer storage medium | |
CN112528616B (en) | Service form generation method and device, electronic equipment and computer storage medium | |
CN115002200A (en) | User portrait based message pushing method, device, equipment and storage medium | |
CN111652278A (en) | User behavior detection method and device, electronic equipment and medium | |
CN113051480A (en) | Resource pushing method and device, electronic equipment and storage medium | |
US11526811B1 (en) | Method for predicting trip purposes using unsupervised machine learning techniques | |
CN113434678B (en) | Item type-based item reminding method, device, equipment and storage medium | |
CN111930897B (en) | Patent retrieval method, device, electronic equipment and computer-readable storage medium | |
CN113505273A (en) | Data sorting method, device, equipment and medium based on repeated data screening | |
CN112948705A (en) | Intelligent matching method, device and medium based on policy big data | |
CN114708073B (en) | Intelligent detection method and device for surrounding mark and serial mark, electronic equipment and storage medium | |
CN103955526B (en) | Data storage method and device | |
CN115221323A (en) | Cold start processing method, device, equipment and medium based on intention recognition model | |
CN113344674A (en) | Product recommendation method, device, equipment and storage medium based on user purchasing power | |
CN112507207B (en) | Travel recommendation method and device | |
CN113505117A (en) | Data quality evaluation method, device, equipment and medium based on data indexes | |
CN113707302A (en) | Service recommendation method, device, equipment and storage medium based on associated information |
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 |