CN111125369A

CN111125369A - Tacit degree detection method, equipment, server and readable storage medium

Info

Publication number: CN111125369A
Application number: CN201911178888.7A
Authority: CN
Inventors: 许剑勇
Original assignee: OneConnect Financial Technology Co Ltd Shanghai
Current assignee: OneConnect Smart Technology Co Ltd; OneConnect Financial Technology Co Ltd Shanghai
Priority date: 2019-11-25
Filing date: 2019-11-25
Publication date: 2020-05-08
Also published as: WO2021103594A1

Abstract

The embodiment of the invention discloses a tacit degree detection method, equipment, a server and a readable storage medium, wherein the method comprises the following steps: acquiring a first detection request sent by a first mobile terminal and a second detection request sent by a second mobile terminal; determining original keywords according to voice text information, image information and image text information acquired from a randomly selected target video image; sending the relevant words in the target relevant word set related to the original key words to the first mobile terminal and the second mobile terminal; establishing a target knowledge map according to knowledge units extracted from the target associated word set; the method comprises the steps of receiving a first relevant word sent by a first mobile terminal and a second relevant word sent by a second mobile terminal, and determining the degree of tacit between the first mobile terminal and the second mobile terminal according to a target knowledge graph, the first relevant word and the second relevant word, so that the accuracy and flexibility of determining the relevant words are improved, the user experience is improved, and the interestingness is enhanced.

Description

Tacit degree detection method, equipment, server and readable storage medium

Technical Field

The invention relates to the technical field of associated word determination, in particular to a tacit degree detection method, equipment, a server and a readable storage medium.

Background

The concept of keyword extraction is generated along with the appearance of information retrieval, the development of information methods enables the number of information data to grow exponentially, and in the face of such huge data sets, searching for data meeting query conditions is a big method difficulty. After the concept of keywords is introduced, the application fields of the keywords are more and more extensive.

However, since the extraction of the keywords has certain limitations, in many applications, the accuracy of the processing result obtained by using the keywords as reference information is low. Therefore, how to effectively determine the relevant words has important significance.

Disclosure of Invention

The embodiment of the invention provides a default degree detection method, equipment, a server and a storage medium, which can be used for more effectively determining associated words, improving the accuracy and flexibility of determining the associated words and effectively realizing default degree detection.

In a first aspect, an embodiment of the present invention provides a default degree detection method, including:

acquiring voice text information, image information and image text information in the target video image, and determining original keywords of the target video image according to the voice text information, the image information and the image text information;

determining a target associated word set related to the original keyword according to a preset associated word extraction algorithm, and sending the target associated word set to the first mobile terminal and the second mobile terminal for selection by users of the first mobile terminal and the second mobile terminal;

extracting a knowledge unit from the target associated word set, and establishing a target knowledge graph according to the knowledge unit, wherein the knowledge unit comprises any one or more of entity associated words, relation associated words and attribute associated words;

receiving a first associated word sent by the first mobile terminal and a second associated word sent by the second mobile terminal, and determining the degree of tacitness between the first mobile terminal and the second mobile terminal according to the target knowledge graph, the first associated word and the second associated word.

Further, when determining a target related word set related to the original keyword according to a preset related word extraction algorithm to obtain voice text information, image information, and image text information in the target video image, the method is specifically configured to:

inquiring the associated data related to the original key words from the network according to a preset inquiry tool;

segmenting the associated data to obtain a plurality of associated words, and determining the parts of speech of the associated words;

and determining the associated words with the parts of speech being preset parts of speech and the original keywords to form the target associated word set according to the parts of speech of the associated words.

Further, after the associated word with the part of speech determined as the preset part of speech and the original keyword form the target associated word set, the method further comprises:

determining semantic similarity between the relevant words in the target relevant word set;

determining a plurality of associated words with semantic similarity larger than a preset similarity threshold in the target associated word set as repeated associated words, and performing de-duplication processing on the plurality of associated words.

Further, when the target knowledge graph is established according to the knowledge unit, the method is specifically configured to:

determining entity associated words with the same semantic category as parallel entity associated words under the same semantic category according to the entity associated words and the relation associated words;

determining that the attribute information with the same entity associated word is a parallel attribute associated word under the same entity associated word according to the entity associated word, the attribute associated word and the relation associated word;

and establishing a target knowledge graph according to the relation among the entity associated words, the parallel entity associated words, the attribute associated words, the parallel attribute associated words and the relation associated words.

Further, when the target knowledge graph is established according to the relationship among the entity associated words, parallel entity associated words, attribute associated words, parallel attribute associated words, and relationship associated words, the method is specifically configured to:

determining the entity associated words and the parallel entity associated words as nodes of a first level;

determining the attribute associated words and the parallel attribute associated words as nodes of a second level;

determining the corresponding relation between the nodes in the first hierarchy and the nodes in the second hierarchy according to the relation associated words;

and connecting the nodes in the first hierarchy with the nodes in the second hierarchy according to the corresponding relation between the nodes in the first hierarchy and the nodes in the second hierarchy to obtain the target knowledge graph.

Further, when determining the degree of tacit between the first mobile terminal and the second mobile terminal according to the relationship between the associated words in the target knowledge graph, the method is specifically configured to:

determining the degree of association between the associated words selected by the first mobile terminal and the associated words selected by the second mobile terminal according to the relationship between the associated words in the target knowledge graph and the preset association weight of the associated words, wherein the preset association weight is determined according to the frequency of the associated words appearing in the query process;

and determining the tacit degree between the first mobile terminal and the second mobile terminal according to the preset corresponding relation between the association degree and the tacit degree.

Further, before determining the association degree between the associated word selected by the first mobile terminal and the associated word selected by the second mobile terminal according to the relationship between the associated words in the target knowledge graph and the preset association weight of each associated word, the method further comprises:

assigning the same association weight to each level in the target knowledge graph, wherein the sum of the association weights of each level is 1;

distributing the same preset association weight to each associated word in each level according to the association weight of each level and the number of the associated words in each level, wherein the sum of the preset association weights of each associated word in each level is equal to the association weight corresponding to each level;

when determining the association degree between the associated word selected by the first mobile terminal and the associated word selected by the second mobile terminal according to the relationship between the associated words in the target knowledge graph and the preset association weight of each associated word, the method is specifically configured to:

determining whether the associated word selected by the first mobile terminal and the associated word selected by the second mobile terminal belong to the same level;

if the relevant word selected by the first mobile terminal and the relevant word selected by the second mobile terminal belong to the same level, acquiring a difference value between a preset association weight of the relevant word selected by the first mobile terminal and a preset association weight of the relevant word selected by the second mobile terminal, and determining that the difference value between 1 and the difference value is the association degree between the relevant word selected by the first mobile terminal and the relevant word selected by the second mobile terminal;

and if the relevant word selected by the first mobile terminal and the relevant word selected by the second mobile terminal belong to different levels, determining the difference of the association weights of the levels in the different levels as the association degree between the relevant word selected by the first mobile terminal and the relevant word selected by the second mobile terminal.

In a second aspect, an embodiment of the present invention provides a default degree detection device, where the default degree detection device includes a unit configured to execute the data processing method of the first aspect.

In a third aspect, an embodiment of the present invention provides a server, including a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are connected to each other, where the memory is used to store a computer program that supports a data processing device to execute the above method, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method of the first aspect.

In a fourth aspect, the present invention provides a computer-readable storage medium, which stores a computer program, where the computer program is executed by a processor to implement the method of the first aspect.

According to the embodiment of the invention, the default degree detection device can determine the original keywords of the target video image according to the voice text information, the image information and the image text information extracted from the target video image, and determine the target associated word set related to the original keywords according to the preset associated word extraction algorithm, so that the accuracy and the flexibility of determining the associated words are improved. The relevant words in the target relevant word set are sent to the first mobile terminal and the second mobile terminal so as to be selected by users of the first mobile terminal and the second mobile terminal, and the target knowledge graph is established according to the knowledge units extracted from the target relevant word set so as to determine the tacit degree between the first mobile terminal and the second mobile terminal according to the relation between the relevant words in the target knowledge graph and the relevant words selected by the users of the first mobile terminal and the second mobile terminal, so that the tacit degree detection is effectively realized, the user experience is improved, and the interestingness is enhanced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic flow chart of a default degree detection method provided in an embodiment of the present invention;

fig. 2 is a schematic flow chart of another default degree detection method provided in the embodiment of the present invention;

FIG. 3 is a schematic diagram of a knowledge-graph provided by an embodiment of the present invention;

fig. 4 is a schematic block diagram of a default degree detection device according to an embodiment of the present invention;

fig. 5 is a schematic block diagram of a server according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The default degree detection method provided by the embodiment of the invention can be executed by a default degree detection device, wherein the default degree detection device can be applied to a server. In some embodiments, the server may be disposed on a smart terminal such as a mobile phone, a computer, a tablet, a smart watch, and the like. In some embodiments, the default-degree detection device may be installed on the server, in some embodiments, the default-degree detection device may be spatially independent from the server, in some embodiments, the default-degree detection device may be a component of the server, i.e., the server includes the default-degree detection device.

In the embodiment of the present invention, tacit degree detection equipment may obtain a first detection request sent by a first mobile terminal, obtain a second detection request sent by a second mobile terminal, and randomly select a target video image from a preset database, where the first detection request carries a terminal identifier of the second mobile terminal, and the second detection request carries a terminal identifier of the first mobile terminal; acquiring voice text information, image information and image text information in the target video image, and determining original keywords of the target video image according to the voice text information, the image information and the image text information; determining a target associated word set related to the original keyword according to a preset associated word extraction algorithm, and sending associated words in the target associated word set to the first mobile terminal and the second mobile terminal for selection by users of the first mobile terminal and the second mobile terminal; extracting a knowledge unit from the target associated word set, and establishing a target knowledge graph according to the knowledge unit, wherein the knowledge unit comprises any one or more of entity associated words, relation associated words and attribute associated words; receiving the relevant words selected by the users of the first mobile terminal and the second mobile terminal, determining the association degree between the relevant words selected by the first mobile terminal and the relevant words selected by the second mobile terminal according to the relation between the relevant words in the target knowledge graph, and determining the tacit degree between the first mobile terminal and the second mobile terminal according to the corresponding relation between the preset association degree and the default degree.

The default degree detection method of the embodiment of the invention is schematically described below with reference to the accompanying drawings.

Referring to fig. 1, fig. 1 is a schematic flowchart of a default degree detection method according to an embodiment of the present invention, and as shown in fig. 1, the method may be executed by a default degree detection device, and a specific explanation of the default degree detection device is as described above, and is not described herein again. Specifically, the method of the embodiment of the present invention includes the following steps.

S101: the method comprises the steps of obtaining a first detection request sent by a first mobile terminal and a second detection request sent by a second mobile terminal, and randomly selecting a target video image from a preset database.

In the embodiment of the present invention, the tacit degree detection device may obtain a first detection request sent by a first mobile terminal and a second detection request sent by a second mobile terminal, and randomly select a target video image from a preset database. The first detection request carries a terminal identifier of a second mobile terminal, and the second detection request carries a terminal identifier of a first mobile terminal; in some embodiments, the terminal identifier of the second mobile terminal carried by the first detection request is used to indicate that the first mobile terminal requests to perform tacit degree detection with the second mobile terminal; and the terminal identifier of the first mobile terminal carried by the second detection request is used for indicating the second mobile terminal to request to perform tacit degree detection with the first mobile terminal.

In an embodiment, the tacit degree detection device may obtain detection requests sent by more than two mobile terminals, and the detection request sent by each mobile terminal may carry one or more terminal identifiers.

For example, it is assumed that the tacit degree detection device obtains a first detection request sent by the mobile terminal 1, where the first detection request carries the terminal identifier 2 of the mobile terminal 2 and the terminal identifier 3 of the mobile terminal 3; the default contract degree detection device acquires a second detection request sent by the mobile terminal 2, wherein the second detection request carries the terminal identifier 1 of the mobile terminal 1 and the terminal identifier 3 of the mobile terminal 3; and the default contract degree detection device acquires a third detection request sent by the mobile terminal 3, wherein the third detection request carries the terminal identifier 1 of the mobile terminal 1 and the terminal identifier 2 of the mobile terminal 2. Therefore, the first mobile terminal, the second mobile terminal and the third mobile terminal can be determined to perform tacit detection simultaneously, so that the tacit detection device sends the target video image randomly selected from the preset database to the first mobile terminal, the second mobile terminal and the third mobile terminal, and the tacit between the first mobile terminal, the second mobile terminal and the third mobile terminal can be determined subsequently.

For another example, it is assumed that the tacit degree detection device obtains a first detection request sent by the mobile terminal 1, where the first detection request carries the terminal identifier 2 of the mobile terminal 2 and the terminal identifier 3 of the mobile terminal 3; the default contract degree detection device acquires a second detection request sent by the mobile terminal 2, wherein the second detection request carries the terminal identifier 1 of the mobile terminal 1; and the default contract degree detection device acquires a third detection request sent by the mobile terminal 3, wherein the third detection request carries the terminal identifier 2 of the mobile terminal 2. Therefore, mutual acquaintance detection between the first mobile terminal and the second mobile terminal and mutual acquaintance detection between the first mobile terminal and the third mobile terminal can be determined, so that the acquaintance detection equipment can send the target video image randomly selected from the preset database to the first mobile terminal, the second mobile terminal and the third mobile terminal, and convenience is brought to subsequent determination of acquaintance of the first mobile terminal and the second mobile terminal and acquaintance of the first mobile terminal and the third mobile terminal.

S102: and acquiring voice text information, image information and image text information in the target video image, and determining the original keywords of the target video image according to the voice text information, the image information and the image text information.

In the embodiment of the present invention, the tacit degree detection device may obtain the voice text information, the image information, and the image text information in the target video image, and determine the original keyword of the target video image according to the voice text information, the image information, and the image text information.

In an embodiment, when the tacit degree detection device acquires the voice text information, the image information, and the image text information in the target video image, the tacit degree detection device may determine the voice text information corresponding to the voice information in the target video image according to voice recognition. The default degree detection device may perform frame decomposition on the target video image to obtain a plurality of image frames, and determine image information in each image frame according to image recognition. The default contract degree detection device can label the field of each image frame to obtain field image data of each image frame, label text information in the field image data to obtain text label information, and accordingly identify the image text information in the field image data according to the text label information.

In one embodiment, the default degree detection device may determine whether voice information exists in the target video image before determining voice text information corresponding to the voice information in the target video image according to voice recognition, where the voice information includes audio information, and may determine the voice text information corresponding to the voice information in the target video image according to voice recognition if determining that the voice information exists in the target video image.

In one embodiment, when determining the voice text information corresponding to the voice information in the target video image according to voice recognition, the default degree detection device may acquire a voice signal of the target video image, perform windowing and framing processing on the voice signal according to a first preset duration, and split the voice signal into a plurality of voice frames of a second preset duration; in some embodiments, the second predetermined duration is less than or equal to the first predetermined duration. The default degree detection device can perform denoising processing on each section of the voice frames with the second preset duration, convert all the denoised voice frames with the second preset duration into a voice signal sequence, and input the voice signal sequence into a preset voice recognition model for recognition, so as to determine voice text information corresponding to the voice signal sequence.

In one embodiment, when the default degree detection device performs frame decomposition on the target video image to obtain a plurality of image frames and determines image information in each image frame according to image recognition, the default degree detection device may split the target video image according to a preset period to obtain a plurality of image frames and determine the image information in each image frame through image recognition; in certain embodiments, the image information includes, but is not limited to, character information, animal information, etc. in the target video image.

In an embodiment, in the process of determining the image text information, the default degree detection device may label each image frame to obtain field label information, determine a position of the field information in each image frame according to the field label information, and cut each image frame according to the position of the field information to obtain field image data corresponding to the position of the field information. The tacit degree detection device can acquire text information in the field image data, label the text information in the field image data to obtain text label information, and then process the text label information and the field image data based on an OCR recognition model to recognize image text information in the field image data.

Therefore, the voice text information, the image information and the image text information in the target video image can be effectively determined by the embodiment, so that the original keywords of the target video image can be more effectively determined.

S103: and determining a target associated word set related to the original keyword according to a preset associated word extraction algorithm, and sending the target associated word set to the first mobile terminal and the second mobile terminal.

In the embodiment of the present invention, the default degree detection device may determine, according to a preset associated word extraction algorithm, a target associated word set related to the original keyword, and send the associated words in the target associated word set to the first mobile terminal and the second mobile terminal, so as to be selected by users of the first mobile terminal and the second mobile terminal.

In one embodiment, when the default degree detection device determines the target associated word set related to the original keyword according to a preset associated word extraction algorithm, the default degree detection device may query associated data related to the original keyword from a network according to a preset query tool, perform word segmentation on the associated data to obtain a plurality of associated words, and determine parts of speech of the plurality of associated words. The default contract degree detection device can determine the associated words with the parts of speech being preset parts of speech according to the parts of speech of the associated words and the target associated word set formed by the original keywords. In some embodiments, the predetermined query tools include, but are not limited to, encyclopedia, discordance, Chinese dictionary, and the like.

In one embodiment, the predetermined part of speech includes, but is not limited to, a noun or an adjective part of speech, and the tacit detection apparatus may determine, according to the parts of speech of the plurality of associated words, that the part of speech is an associated word of an adjective or a noun and the original keyword constitutes the target associated word set.

In an embodiment, when determining that a relevant word with a part of speech being a preset part of speech and the original keyword form the target relevant word set, the default degree detection device may obtain a frequency of occurrence of each relevant word in the relevant word set in a query process, and determine that the relevant word with the frequency being greater than a preset frequency threshold and the original keyword form the target relevant word set.

In one embodiment, when determining that the associated words with the part of speech being the preset part of speech and the original keywords form the target associated word set, the default degree detection device may obtain the frequency of occurrence of each associated word in the target associated word set in the query process, rank each associated word in the target associated word set according to the order of the frequency from high to low, extract the top n associated words, and add the top n associated words to the target associated word set. For example, the related words arranged in the top 10 are extracted and added to the target related word set. In certain embodiments, n is a positive integer.

In one embodiment, the default contract degree detection device may perform circular query by using a query tool according to m related words arranged in the top m related words in the n related words, and add the related words queried in k times in a target related word set, where n is greater than or equal to m, and m is greater than or equal to k. For example, the default degree detection device may select the related words arranged in the top 3 from the related words arranged in the top 10, circularly query the related words by using a query tool according to the 3 related words, add the related words into the target related word set, and end after 3 times of circulation. By the mode of circular query, more effective associated words can be determined.

In one embodiment, after determining that the associated words with the part of speech being the preset part of speech and the original keyword form the target associated word set, the default degree detection device may determine semantic similarity between the associated words in the target associated word set, determine multiple associated words in the target associated word set, the semantic similarity of which is greater than a preset similarity threshold, as repeated associated words, and perform deduplication processing on the multiple associated words. In some embodiments, the semantic similarity between the same associated words is 100%. By the implementation, repeated associated words or associated words with similarity greater than a preset similarity threshold can be subjected to deduplication processing, so that the calculation complexity is reduced, and the processing efficiency is improved.

S104: and extracting a knowledge unit from the target associated word set, and establishing a target knowledge graph according to the knowledge unit.

In the embodiment of the invention, the default degree detection device can extract a knowledge unit from the target associated word set and establish a target knowledge map according to the knowledge unit. In some embodiments, the knowledge unit comprises any one or more of entity associated words, relation associated words and attribute associated words; in some embodiments, the target knowledge graph is composed of any one or more of entity associated words, relation associated words and attribute associated words.

S105: receiving a first associated word sent by the first mobile terminal and a second associated word sent by the second mobile terminal, and determining the degree of tacitness between the first mobile terminal and the second mobile terminal according to the target knowledge graph, the first associated word and the second associated word.

In the embodiment of the present invention, the default degree detection device may receive the associated words selected by the users of the first mobile terminal and the second mobile terminal, and determine the default degree between the first mobile terminal and the second mobile terminal according to the relationship between the associated words in the target knowledge graph.

In one embodiment, the default contract degree detection device may determine the degree of association between the related word selected by the first mobile terminal and the related word selected by the second mobile terminal according to the relationship between the related words in the target knowledge graph and a preset association weight of each related word, where the preset association weight is determined according to the frequency of occurrence of the related word in the query process. The default degree detection device may determine the default degree between the first mobile terminal and the second mobile terminal according to a preset correspondence between the association degree and the default degree.

In one embodiment, if the first mobile terminal and the second mobile terminal select the same associated word, the understandings of the understandings are considered; and if the relevant words selected by the first mobile terminal and the second mobile terminal are different, determining the association degree between the relevant words selected by the first mobile terminal and the relevant words selected by the second mobile terminal according to the relationship between the relevant words in the target knowledge graph and the preset association weight of the relevant words. And determining the tacit degree between the first mobile terminal and the second mobile terminal according to the preset corresponding relation between the association degree and the tacit degree.

In one embodiment, before determining the degree of acquaintance between the first mobile terminal and the second mobile terminal, each level in the target knowledge graph may be assigned with the same association weight, and the sum of the association weights of the levels is 1, and each related word in each level is assigned with the same preset association weight according to the association weight of each level and the number of related words in each level, and the sum of the preset association weights of each related word in each level is equal to the association weight corresponding to each level.

In one embodiment, when determining the association degree between the associated word selected by the first mobile terminal and the associated word selected by the second mobile terminal according to the relationship between the associated words in the target knowledge graph and the preset association weight of each associated word, whether the related word selected by the first mobile terminal and the related word selected by the second mobile terminal belong to the same level or not can be determined, if the related word selected by the first mobile terminal and the related word selected by the second mobile terminal belong to the same level, obtaining the difference value between the preset association weight of the associated word selected by the first mobile terminal and the preset association weight of the associated word selected by the second mobile terminal, determining the difference between 1 and the difference value as the degree of association between the associated word selected by the first mobile terminal and the associated word selected by the second mobile terminal; and if the relevant word selected by the first mobile terminal and the relevant word selected by the second mobile terminal belong to different levels, determining the difference of the association weights of the levels in the different levels as the association degree between the relevant word selected by the first mobile terminal and the relevant word selected by the second mobile terminal.

Therefore, through the implementation mode, the tacit detection between the terminals can be effectively realized, and the effectiveness of the tacit detection is improved.

Taking fig. 3 as an example, fig. 3 is a schematic diagram of a knowledge graph provided in an embodiment of the present invention, and it is assumed that the associated words selected by the first mobile terminal include china 31, shanghai 32, supermarket 33, fruit 34, and pear 341, and the associated words selected by the second mobile terminal include china 31, shanghai 32, supermarket 33, fruit 34, and apple 344, where the first mobile terminal and the second mobile terminal both select china 31, shanghai 32, supermarket 33, and fruit 34, and then the association degrees of china 31, shanghai 32, supermarket 33, and fruit 34 do not need to be calculated, and only the association degree of pear 341 and apple 344 needs to be calculated. If the preset association weight of the pear 341 is 0.7 and the preset association weight of the apple 344 is 0.8, it may be determined that the association degree between the pear 341 and the apple 344 is: 1- (0.8-0.7) ═ 0.9, it can be determined that the degree of ambiguity between the first mobile terminal and the second mobile terminal is 90%.

In one embodiment, each related word on the target knowledge graph has a preset related weight, if a related word is a keyword extracted from the target video image, the preset related weight is 1, and if the related word is not a keyword extracted from the target video image, the preset related weight may be determined according to the frequency of the related word appearing in the query process.

Also taking fig. 3 as an example, assuming that the keywords extracted from the target video image include china 31, shanghai 32, supermarket 33 and fruit 34, it may be determined that the preset association weight of the entity associated word china 31, shanghai 32, supermarket 33 and fruit 34 is 1, if the frequency of occurrence of pear 341 in the query process is 5 times, the frequency of occurrence of watermelon 342 in the query process is 4 times, the frequency of occurrence of hami melon 343 in the query process is 3 times, the frequency of occurrence of apple 344 in the query process is 6 times, and the total query times is 7 times, it may be determined that the preset association weight of pear 341 is 5/7, the preset association weight of watermelon 342 is 4/7, the preset association weight of hami melon 343 is 3/7, and the preset association weight of apple 344 is 6/7.

In the embodiment of the invention, the default degree detection device extracts the voice text information, the image information and the image text information from the target video image, determines the original keywords of the target video image according to the voice text information, the image information and the image text information, and determines the target associated word set related to the original keywords, so that the accuracy and the flexibility of determining the associated words are improved. The default contract degree detection device can send the relevant words in the target relevant word set to the first mobile terminal and the second mobile terminal so as to be selected by users of the first mobile terminal and the second mobile terminal; the method comprises the steps of establishing a target knowledge graph according to knowledge units extracted from a target related word set, receiving related words selected by users of a first mobile terminal and a second mobile terminal, and determining the tacit degree between the first mobile terminal and the second mobile terminal according to the relation between the related words in the target knowledge graph, so that the tacit degree detection effectiveness is improved, the user experience is improved, and the interestingness is enhanced.

Referring to fig. 2, fig. 2 is a schematic flowchart of another default-degree detection method according to an embodiment of the present invention, and as shown in fig. 2, the method may be executed by a default-degree detection device, and a specific explanation of the default-degree detection device is as described above, and is not described here again. The difference between the embodiment of the present invention and the method described in fig. 1 is that the embodiment of the present invention schematically illustrates how to establish the target knowledge graph, and specifically, the method of the embodiment of the present invention includes the following steps.

S201: acquiring voice text information, image information and image text information in a target video image, and determining an original keyword of the target video image according to the voice text information, the image information and the image text information.

In the embodiment of the invention, the tacit degree detection device can acquire the voice text information, the image information and the image text information in the target video image, and determine the original keywords of the target video image according to the voice text information, the image information and the image text information.

S202: and determining a target associated word set related to the original keyword according to a preset associated word extraction algorithm.

In the embodiment of the invention, the default degree detection device can determine the target associated word set related to the original keyword according to a preset associated word extraction algorithm.

S203: and extracting a knowledge unit from the target related word set, wherein the knowledge unit comprises any one or more of entity related words, relation related words and attribute related words.

In the embodiment of the present invention, the default degree detection device may extract a knowledge unit from the target associated word set, where the knowledge unit includes any one or more of an entity associated word, a relationship associated word, and an attribute associated word. In some embodiments, the attribute associated word comprises an attribute and/or an attribute value.

In some embodiments, the entity-related word refers to a specific thing that is distinguishable and independent, such as a certain person, a certain city, a certain plant, etc., a certain commodity, etc. Such as "china", "italy", "canada", etc., entities are the most basic elements in knowledge-graphs.

In some embodiments, an attribute refers to an attribute that is pointed to from one entity associated word, with different attribute types corresponding to edges of different types of attributes, e.g., "area", "volume", "diameter", "longitude", "latitude", "population", "capital" being several different attributes. In some embodiments, the attribute value mainly refers to a value of an attribute, such as an area of 300 ten thousand square kilometers, a population of 500 ten thousand square kilometers, and a diameter of 2 m.

In one embodiment, the knowledge unit may further include semantic information, which refers to a set of entity-related words with the same characteristics, such as words summarizing a category of things like a country, a nation, an animal, a book, and the like, and mainly refers to a set, a category, an object type, a category of things, such as people, geography, and the like.

S204: and determining the entity associated words with the same semantic category as the parallel entity associated words in the same semantic category according to the entity associated words and the relation associated words.

In the embodiment of the invention, the default degree detection device can determine that the entity associated words with the same semantic category are parallel entity associated words in the same semantic category according to the entity associated words and the relation associated words.

S205: and determining that the attribute information with the same entity associated word is a parallel attribute associated word under the same entity associated word according to the entity associated word, the attribute associated word and the relation associated word.

In the embodiment of the present invention, the default contract degree detection device may determine, according to the entity related word, the attribute related word and the relationship related word, that the attribute information of the same entity related word is a parallel attribute related word under the same entity related word.

S206: and establishing a target knowledge graph according to the relation among the entity associated words, the parallel entity associated words, the attribute associated words, the parallel attribute associated words and the relation associated words.

In the embodiment of the invention, the default degree detection device can establish the target knowledge graph according to the relation among the entity associated words, the parallel entity associated words, the attribute associated words, the parallel attribute associated words and the relation associated words.

In one embodiment, the default contract degree detection device may determine that the entity related word and the parallel entity related word are nodes in a first hierarchy, determine that the attribute related word and the parallel attribute related word are nodes in a second hierarchy, determine a correspondence between a node in the first hierarchy and a node in the second hierarchy according to the relationship related word, and connect a node in the first hierarchy and a node in the second hierarchy according to a correspondence between a node in the first hierarchy and a node in the second hierarchy to obtain the target knowledge graph.

In one embodiment, different relationships exist between different entity-related words, and on the knowledge graph, the relationship is a function for mapping k nodes (entity-related words, semantic classes, attributes, attribute values) to Boolean values. The relation information in the target knowledge graph comprises semantic class-relation-entities, such as country-China, nationality-Han nationality and the like, entity-relation-entities, such as China-capital-Beijing, China-direct prefecture City-Chongqing and the like, and entity-attribute values, such as Chongqing-population-3000 ten thousand, Shanghai-area-50 ten thousand square kilometers and the like.

Taking fig. 3 as an example, assuming that the determined target related word set includes related words such as china 31, shanghai 32, supermarket 33, fruit 34, pear 341, watermelon 342, hami melon 343, apple 344, etc., the determined semantic categories include china 31, the entity related words belonging to the china 31 of the same semantic category include shanghai 32, the entity related word supermarket 33 is a lower attribute of the entity related word shanghai 32, the entity related word fruit 34 is a lower attribute of the entity related word supermarket 33, the lower parallel attribute related words belonging to the same entity related word fruit 34 include pear 341, watermelon 342, hami melon 343, apple 344, the relationship related word between the entity related word supermarket 33 and the entity related word fruit 34 is the related word 35, and the lower attribute of the apple 344 includes apple vinegar 3441 and apple stem 3442, so that the target knowledge map shown in fig. 3 can be established.

According to the embodiment of the invention, the default degree detection device can determine the entity associated words with the same semantic category as the parallel entity associated words in the same semantic category according to the entity associated words and/or the relation associated words in the knowledge unit extracted from the target associated word set; determining attribute information with the same entity associated word as a parallel attribute associated word under the same entity associated word according to the entity associated word, the attribute associated word and the relation associated word in the knowledge unit; and establishing an effective target knowledge graph according to the relation among the entity associated words, the parallel entity associated words, the attribute associated words, the parallel attribute associated words and the relation associated words so as to improve the effectiveness of default degree detection.

The embodiment of the invention also provides a default degree detection device, which is used for executing the unit of the method. Specifically, referring to fig. 4, fig. 4 is a schematic block diagram of a default degree detection device according to an embodiment of the present invention. The default degree detection device of the embodiment includes: an acquisition unit 401, a determination unit 402, a transmission unit 403, a creation unit 404, and a reception unit 405;

an obtaining unit 401, configured to obtain a first detection request sent by a first mobile terminal, obtain a second detection request sent by a second mobile terminal, and randomly select a target video image from a preset database, where the first detection request carries a terminal identifier of the second mobile terminal, and is used to request to perform tacit detection with the second mobile terminal, and the second detection request carries a terminal identifier of a first mobile terminal, and is used to request to perform tacit detection with the first mobile terminal;

a determining unit 402, configured to acquire voice text information, image information, and image text information in the target video image, and determine an original keyword of the target video image according to the voice text information, the image information, and the image text information;

a sending unit 403, configured to determine a target related word set related to the original keyword according to a preset related word extraction algorithm, and send the target related word set to the first mobile terminal and the second mobile terminal, so that users of the first mobile terminal and the second mobile terminal can select the target related word set;

the establishing unit 404 is configured to extract a knowledge unit from the target associated word set, and establish a target knowledge graph according to the knowledge unit, where the knowledge unit includes any one or more of an entity associated word, a relationship associated word, and an attribute associated word;

a receiving unit 405, configured to receive a first related word sent by the first mobile terminal and a second related word sent by the second mobile terminal, and determine a degree of tacit between the first mobile terminal and the second mobile terminal according to the target knowledge graph, the first related word, and the second related word.

Further, when the sending unit 403 determines, according to a preset associated word extraction algorithm, a target associated word set related to the original keyword to obtain the speech text information, the image information, and the image text information in the target video image, specifically:

Further, after the sending unit 403 determines that the associated word with the part of speech being the preset part of speech and the original keyword form the target associated word set, it is further configured to:

Further, when the establishing unit 404 establishes the target knowledge graph according to the knowledge unit, it is specifically configured to:

Further, when the establishing unit 404 establishes the target knowledge graph according to the relationship among the entity related words, parallel entity related words, attribute related words, parallel attribute related words, and relationship related words, the establishing unit is specifically configured to:

Further, when the receiving unit 405 determines the degree of understanding between the first mobile terminal and the second mobile terminal according to the relationship between the associated words in the target knowledge graph, the receiving unit is specifically configured to:

Further, before the receiving unit 405 determines the association degree between the relevant word selected by the first mobile terminal and the relevant word selected by the second mobile terminal according to the relationship between the relevant words in the target knowledge graph and the preset association weight of the relevant words, the receiving unit is further configured to:

when determining the association degree between the associated word selected by the first mobile terminal and the associated word selected by the second mobile terminal according to the relationship between the associated words in the target knowledge graph and the preset association weight of each associated word, the receiving unit 405 is specifically configured to:

In the embodiment of the invention, the default degree detection device can determine the original keywords of the target video image according to the voice text information, the image information and the image text information extracted from the target video image, and determine the target associated word set related to the original keywords according to the preset associated word extraction algorithm, so that the accuracy and the flexibility of determining the associated words are improved. The relevant words in the target relevant word set are sent to the first mobile terminal and the second mobile terminal so as to be selected by users of the first mobile terminal and the second mobile terminal, and the target knowledge graph is established according to the knowledge units extracted from the target relevant word set so as to determine the degree of tacitness between the first mobile terminal and the second mobile terminal according to the relation between the relevant words in the target knowledge graph and the relevant words selected by the users of the first mobile terminal and the second mobile terminal, so that the user experience is improved, and the interestingness is enhanced.

Referring to fig. 5, fig. 5 is a schematic block diagram of a server according to an embodiment of the present invention. The server in this embodiment as shown in the figure may include: one or more processors 501; one or more input devices 502, one or more output devices 503, and memory 504. The processor 501, the input device 502, the output device 503, and the memory 504 are connected by a bus 505. The memory 504 is used to store a computer program comprising program instructions and the processor 501 is used to execute the program instructions stored by the memory 504. Wherein the processor 501 is configured to call the program instruction to perform:

Further, when the processor 501 determines, according to a preset associated word extraction algorithm, a target associated word set related to the original keyword to obtain the speech text information, the image information, and the image text information in the target video image, the processor is specifically configured to:

Further, after the processor 501 determines that the associated word with the part of speech being the preset part of speech and the original keyword form the target associated word set, the processor is further configured to:

Further, when the processor 501 establishes the target knowledge graph according to the knowledge unit, it is specifically configured to:

Further, when the processor 501 establishes the target knowledge graph according to the relationship among the entity related words, parallel entity related words, attribute related words, parallel attribute related words, and relationship related words, the processor is specifically configured to:

Further, when determining the degree of understanding between the first mobile terminal and the second mobile terminal according to the relationship between the associated words in the target knowledge graph, the processor 501 is specifically configured to:

Further, before the processor 501 determines the association degree between the associated word selected by the first mobile terminal and the associated word selected by the second mobile terminal according to the relationship between the associated words in the target knowledge graph and the preset association weight of each associated word, the processor is further configured to:

when determining the association degree between the associated word selected by the first mobile terminal and the associated word selected by the second mobile terminal according to the relationship between the associated words in the target knowledge graph and the preset association weight of each associated word, the processor 501 is specifically configured to:

In the embodiment of the invention, the server can determine the original keywords of the target video image according to the voice text information, the image information and the image text information extracted from the target video image, and determine the target associated word set related to the original keywords according to the preset associated word extraction algorithm, so that the accuracy and the flexibility of determining the associated words are improved. The relevant words in the target relevant word set are sent to the first mobile terminal and the second mobile terminal so as to be selected by users of the first mobile terminal and the second mobile terminal, and the target knowledge graph is established according to the knowledge units extracted from the target relevant word set so as to determine the degree of tacitness between the first mobile terminal and the second mobile terminal according to the relation between the relevant words in the target knowledge graph and the relevant words selected by the users of the first mobile terminal and the second mobile terminal, so that the user experience is improved, and the interestingness is enhanced.

It should be understood that, in the embodiment of the present invention, the Processor 501 may be a Central Processing Unit (CPU), and may also be other general processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable gate arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

Input devices 502 may include a touch pad, microphone, etc., and output devices 503 may include a display (LCD, etc.), speakers, etc.

The memory 504 may include a read-only memory and a random access memory, and provides instructions and data to the processor 501. A portion of the memory 504 may also include non-volatile random access memory. For example, the memory 504 may also store device type information.

In specific implementation, the processor 501, the input device 502, and the output device 503 described in this embodiment of the present invention may execute the implementation described in the method embodiment of the default detection method provided in this embodiment of the present invention, and may also execute the implementation of the front-end client and the back-end server described in this embodiment of the present invention, which is not described herein again.

The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the default detection method described in the embodiment of the present invention is implemented, which is not described herein again.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a readable storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned readable storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The above description is only a part of the embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.

Claims

1. A method for detecting a default degree is characterized by comprising the following steps:

the method comprises the steps of obtaining a first detection request sent by a first mobile terminal, obtaining a second detection request sent by a second mobile terminal, and randomly selecting a target video image from a preset database, wherein the first detection request carries a terminal identifier of the second mobile terminal and is used for requesting tacit detection with the second mobile terminal, and the second detection request carries a terminal identifier of the first mobile terminal and is used for requesting tacit detection with the first mobile terminal;

determining a target associated word set related to the original keyword according to a preset associated word extraction algorithm, and sending the target associated word set to the first mobile terminal and the second mobile terminal;

2. The method according to claim 1, wherein the determining a target related word set related to the original keyword according to a preset related word extraction algorithm comprises:

3. The method of claim 2, wherein after the determining the associated words with the part of speech being the preset part of speech and the original keywords form the target associated word set, the method further comprises:

4. The method of claim 1, wherein establishing a target knowledge-graph from the knowledge units comprises:

5. The method according to claim 4, wherein the establishing a target knowledge graph according to the relationship among the entity related words, parallel entity related words, attribute related words, parallel attribute related words and relationship related words comprises:

6. The method according to claim 1, wherein the determining the degree of understanding between the first mobile terminal and the second mobile terminal according to the relationship between the relevant words in the target knowledge graph comprises:

7. The method according to claim 6, wherein before determining the degree of association between the related word selected by the first mobile terminal and the related word selected by the second mobile terminal according to the relationship between the related words in the target knowledge graph and the preset association weight of each related word, the method further comprises:

the determining the association degree between the associated word selected by the first mobile terminal and the associated word selected by the second mobile terminal according to the relationship between the associated words in the target knowledge graph and the preset association weight of the associated word comprises:

8. A default degree detection device, characterized by comprising means for performing the method of any of claims 1-7.

9. A server comprising a processor, an input device, an output device, and a memory, the processor, the input device, the output device, and the memory being interconnected, wherein the memory is configured to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method of any of claims 1-7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which is executed by a processor to implement the method of any one of claims 1-7.