Method for determining influence words of language development, method for presenting language development process

Abstract

The application provides a language development influence word determination method and a language development process display method. The language development influence word determination method comprises the following steps: obtaining a user-selected language development starting time, a language development ending time and a target word; determining M candidate words corresponding to the target word based on the language development starting time, the language development ending time and a preset word vector library; for each candidate word, determining a language perplexity of the target word and the candidate word based on M first target sentences containing the target word and M first candidate sentences containing the candidate word; and determining an influence word influencing the development of the target word based on the language perplexity of the target word and each candidate word. According to the technical scheme provided by the application, the acceptable degree of the candidate word can be known through the language perplexity, and the influence word influencing the development of the target word is determined through the language perplexity of the candidate word, so that the purpose of determining which influence word influences the development track of the language in the development process of the language is achieved.

Description

Technical Field

[0001] This application relates to the field of virtual interactive technology, and in particular to a method for determining the influencing words of language development and a method for displaying the language development process. Background Technology

[0002] With the development of technology, people's understanding of language development is no longer limited to books. They can also gain a more intuitive understanding of the language development process through virtual interaction. Taking the metaverse as an example, the metaverse is a process of linking and creating using technological means. Essentially, it is a virtualization and digitization of the real world, and its development is gradual. The language development process can be displayed in the form of scenarios through the visualization of the metaverse.

[0003] In related virtual interaction technologies, it is usually necessary to use historical records to pre-set target words whose development history needs to be traced back and words that have influenced the development of the target words in the system. Then, the user selects from these target words and the development process of the target word is displayed through visual interaction. However, this method can only trace the development history of the specified target words. Therefore, how to determine the words that influence the development of the target word based on the target words entered by the user is a problem that urgently needs to be solved. Summary of the Invention

[0004] To address the aforementioned technical problems, this application is proposed. Embodiments of this application provide a method for determining the influencing words of language development and a method for demonstrating the language development process.

[0005] In a first aspect, one embodiment of this application provides a method for determining words that influence language development. The method includes: responding to a user's request to explore language development, obtaining the user-selected start time of language development, end time of language development, and target words whose development history needs to be traced back; determining M candidate words corresponding to the target word based on the start time of language development, the end time of language development, and a preset word vector library, where M is a positive integer; for each candidate word, determining the language perplexity of the target word and each candidate word based on M first target sentences containing the target word and M first candidate sentences containing the candidate word; and determining words that influence the development of the target word based on the language perplexity of the target word and each candidate word.

[0006] Secondly, one embodiment of this application provides a method for displaying the language development process. The method includes: responding to a user's input request to trace the development history of a target word; using the language development influence word determination method described in the first aspect above to determine influence words affecting the development of the target word; using a language processing system to determine the motivation and mechanism by which the influence words affect the development of the target word; wherein the motivation is used to characterize the influencing factors affecting the development of the target word, and the mechanism is used to characterize the regularity affecting the development of the target word; based on the motivation and mechanism by which the influence words affect the development of the target word, displaying the dynamic process of the target word's development to the user using a metaverse as a carrier; if the user adjusts the motivation parameters during the display of the dynamic process of the target word's development, then adjusting the dynamic process of the target word's development based on the motivation and mechanism by which the influence words affect the development of the target word, wherein the motivation parameters are used to characterize the degree of influence of the influencing factors on the development of the target word.

[0007] Thirdly, one embodiment of this application provides a device for determining the influencing words of language development. The device includes: an acquisition module, configured to acquire, in response to a user's request to explore language development, the user-selected start time of language development, end time of language development, and a target word whose development history needs to be traced back; a first determination module, configured to determine M candidate words corresponding to the target word based on the start time of language development, the end time of language development, and a preset word vector library, where M is a positive integer; a second determination module, configured to, for each candidate word, determine the language perplexity of the target word and each candidate word based on M first target sentences containing the target word and M first candidate sentences containing the candidate word; and a third determination module, configured to determine the influencing words affecting the development of the target word based on the language perplexity of the target word and each candidate word.

[0008] Fourthly, one embodiment of this application provides a display device for the language development process. The device includes: a first determining module, configured to, in response to a user input requesting a target word that needs to trace the development history, determine an influencing word affecting the development of the target word using the language development influencing word determination method described in the first aspect; a second determining module, configured to, using a language processing system, determine the motivation and mechanism by which the influencing word affects the development of the target word; wherein the motivation is used to characterize the influencing factors affecting the development of the target word, and the mechanism is used to characterize the regularity affecting the development of the target word; a display module, configured to, based on the motivation and mechanism by which the influencing word affects the development of the target word, display the dynamic process of the target word's development to the user using a metaverse as a carrier; and an adjustment module, configured to, if the user adjusts the motivation parameters during the display of the dynamic process of the target word's development, adjust the dynamic process of the target word's development based on the motivation and mechanism by which the influencing word affects the development of the target word, wherein the motivation parameters characterize the degree of influence of the influencing factors on the development of the target word.

[0009] Fifthly, one embodiment of this application provides a computer-readable storage medium storing a computer program for performing the methods described in the first and second aspects.

[0010] In a sixth aspect, one embodiment of this application provides an electronic device, the electronic device comprising: a processor; a memory for storing processor-executable instructions; the processor being configured to perform the methods described in the first and second aspects.

[0011] The method for determining influencing words in language development provided in this application first responds to a user's request by determining the start time and end time of language development, as well as the target word whose development history needs to be traced. Then, based on the end time of language development and a preset word vector library, it determines M candidate words corresponding to the target word. Next, based on a first target sentence containing the target word and M first candidate sentences containing the M candidate words, it determines the language perplexity of each of the M candidate words. Finally, based on the language perplexity of each of the M candidate words, it determines the influencing words that affect the development of the target word. This application's solution, by determining the language perplexity of candidate words through a first target sentence containing the target word and first candidate sentences containing candidate words, can understand the acceptability of candidate words. Furthermore, by determining the language perplexity of candidate words, it identifies the influencing words that affect the development of the target word, thus achieving the goal of determining which influencing words have affected the trajectory of language development. Attached Figure Description

[0012] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0013] Figure 1 The diagram shown is a schematic representation of an implementation environment to which the embodiments of this application apply.

[0014] Figure 2 The diagram shown is a flowchart illustrating a method for determining the influence words of language development provided in an exemplary embodiment of this application.

[0015] Figure 3 The diagram shown is a schematic flowchart of another exemplary embodiment of this application, which describes how, for each candidate word, the language perplexity of the target word and the candidate words is determined based on M first target sentences containing the target word and M first candidate sentences containing the candidate words.

[0016] Figure 4 The diagram shown is a flowchart illustrating a method for determining the influence words of language development provided in another exemplary embodiment of this application.

[0017] Figure 5 The diagram shows a flowchart of an exemplary embodiment of this application, which calculates the language perplexity of at least one first statement and at least one second statement respectively, and determines M first target statements and M first candidate statements using a preset perplexity ranking threshold.

[0018] Figure 6 The diagram shown is a schematic representation of an exemplary embodiment of this application, illustrating the process of determining M candidate words corresponding to a target word based on the start time of language development, the end time of language development, and a preset word vector library.

[0019] Figure 7 The diagram shown is a flowchart illustrating the process of determining the influencing words that affect the development of the target word based on the target word and the linguistic confusion degree of each candidate word, according to an exemplary embodiment of this application.

[0020] Figure 8 The diagram shown is a flowchart illustrating a method for demonstrating the language development process provided in an exemplary embodiment of this application.

[0021] Figure 9 The diagram shown is a schematic representation of a language development influence word determination device provided in an exemplary embodiment of this application.

[0022] Figure 10The diagram shown is a schematic representation of a language development process demonstration device provided in an exemplary embodiment of this application.

[0023] Figure 11 The diagram shown is a structural schematic of an electronic device provided in an exemplary embodiment of this application. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] Language is constantly evolving, and the language we use in our daily lives is subtly influenced by the times and the development of the internet. With the advancement of technology, people's understanding of language development is no longer limited to books; they can also gain a more intuitive understanding of the process of language development through virtual interaction.

[0026] Taking the metaverse as an example, the metaverse is a process of linking and creating using technological means. Essentially, it is a virtualization and digitization of the real world, and its development is gradual. The process of language development can be visualized through the metaverse, presenting it in the form of scenarios. Related virtual interactive technologies typically require pre-setting target words whose development history needs to be traced back, along with words that influenced their development, based on historical records. Users then select from these target words, and the development process of that target word is displayed through visual interaction. However, this method can only trace the development history of a specific target word.

[0027] To determine how to identify words influencing the development of a target word based on user input, the inventors have conducted a series of studies and proposed the technical solution of this application. In the embodiments of this application, in response to a user's request to explore language development, the system obtains the user-selected start time, end time, and target word whose development history needs to be traced back. Based on the start time, end time, and a preset word vector library, M candidate words corresponding to the target word are determined, where M is a positive integer. For each candidate word, based on M first target sentences containing the target word and M first candidate sentences containing the candidate word, the perplexity of both the target word and the candidate words is determined. Based on the perplexity of the target word and each candidate word, the influencing words affecting the development of the target word are determined. By understanding the acceptability of candidate words through their perplexity, and then using the perplexity of candidate words to determine the influencing words affecting the development of the target word, the system achieves the goal of determining which influencing words affect the trajectory of language development.

[0028] Figure 1 The diagram shows an implementation environment applicable to the embodiments of this application. This implementation environment includes a developer system 101, a word determination device for language development influences 102, a language development process display device 103, and a user system 104.

[0029] For example, the developer system 101 may include a word-influence determination device 102 for language development and a language development process display device 103. Of course, the word-influence determination device 102 for language development and the language development process display device 103 may also be peripheral devices, which are not limited here.

[0030] Specifically, the developer system 101 can be used to provide a large number of general and specific scenarios that users can participate in building, and can transmit the instructions and basic settings issued by users through the user system 104 to the language development influence word determination device 102 and the language development process display device 103, so that the language development influence word determination device 102 and the language development process display device 103 can perform corresponding operations.

[0031] Specifically, the language development influence word determination device 102 can be used to determine the influence words that affect the development of the target word. The specific determination method will be described in detail in the following embodiments, and will not be repeated here.

[0032] Specifically, the language development process display device 103 can be used to display the language development process screen generated by the user's instructions and basic settings through the user system 104 to the user.

[0033] Specifically, the user system 104 can be used to issue commands and adjust basic settings, and provide feedback to the developer system 101, as well as receive the language development process display screen 103. The user system 104 can view the language development process display screen 103 through its own screen or by connecting to other external devices with image display capabilities, such as televisions, computers, virtual reality (VR) glasses, etc. There are no limitations on this.

[0034] In practical applications, users can select a target word whose development history they wish to trace back through the user system 104, and then select the time period of the target word's development they wish to explore, i.e., the start time and end time of language development. After selection, the user submits the selection to the developer system 101. The developer system 101 will then transmit the user's selection to the language development influence word determination device 102 and the language development process display device 103. The language development influence word determination device 102 determines the influence words affecting the development of the target word and sends these influence words to the language development process display device 103, which then displays the language development process to the user through the user system 104. The system displays the development process of the target word within a selected time period, provides prompts when influencing words appear, and identifies the driving forces and mechanisms of language development through these influencing words. A driving force parameter adjustment page is provided to the user through the user system 104. By adjusting the driving force parameter values ​​on the page, the user can adjust the degree of influence of different influencing factors on the development of the target word. The language development process display device 103 will then display the language development process after the user adjusts the driving force parameters, based on the driving forces and mechanisms of language development. Furthermore, the user can adjust the driving force parameters at any time during the viewing process to observe different language development trajectories.

[0035] Figure 2 The diagram shown is a flowchart illustrating a method for determining the influence words of language development according to an exemplary embodiment of this application. Figure 2 As shown in the embodiments of this application, the method for determining the influencing words of language development may include the following steps.

[0036] Step S201: In response to the user's request to explore the language development mechanism, obtain the user's selected language development start time, language development end time, and target words for which the development history needs to be traced back.

[0037] For example, a user's request to explore the language development mechanism may include the user's selected start time of language development, end time of language development, and the target word for which the user wants to trace the development history. The start and end times of language development are the same as the start and end times of the target word's development, that is, the development of the target word from the start time to the end time of language development.

[0038] For example, the target word can be a single word, a word class, or multiple word classes. When the target word is a word class or multiple word classes, the language development process of each word will be processed in parallel, that is, multiple words can be simultaneously used to determine the influencing word.

[0039] Specifically, after determining the start and end times of language development, the language start and end corpus is initialized by inputting a large amount of data into it to form language features that conform to the start and end times of language development.

[0040] Step S202: Based on the start time of language development, the end time of language development, and the preset word vector library, determine the M candidate words corresponding to the target word.

[0041] For example, M is a positive integer. Candidate words are synonyms of the target word.

[0042] For example, the preset word vector library consists of multiple word vectors, which contain a large number of words or phrases that are synonyms of the corresponding words. Word vectors are helpful for analyzing the sentiment and meaning of words.

[0043] Step S203: For each candidate word, based on the M first target sentences containing the target word and the M first candidate sentences containing the candidate word, determine the language perplexity of the target word and the candidate word respectively.

[0044] For example, the linguistic perplexity of a word is the linguistic perplexity of the sentence when the word is in it, which measures how well the sentence is acceptable when the word is in it, where acceptability is the degree to which the sentence can be understood by the person reading the sentence when the word is in it.

[0045] For example, the following formula (1) is the formula for calculating language confusion.

[0046]

[0047] Where, Perplexity is the language perplexity, N is the string length of a sentence, S is a sentence, and P(S) is the probability of S occurring as calculated by the language processing system. The language processing system can be a Natural Language Processing (NLP) system.

[0048] For example, the string length of each first target statement containing the target word can be determined first, then the probability of each first target statement appearing can be calculated using a language processing system, and then the language perplexity of each first target statement can be calculated using the above formula (1). Finally, the language perplexity of each first target statement can be added together to obtain the language perplexity of the target word. Similarly, the string length of the first candidate statement containing each candidate word can be determined first, then the probability of each first candidate statement appearing can be calculated using a language processing system, and then the language perplexity of each first candidate statement can be determined using the above formula (1). Finally, the language perplexity of each first candidate statement can be added together to obtain the language perplexity of the candidate word.

[0049] Step S204: Based on the target word and the language perplexity of each candidate word, identify the influencing words that affect the development of the target word.

[0050] For example, an influencing word is a word that affects the development of a target word. During the development of a target word, the emergence of an influencing word may change its part of speech, usage, etc. For instance, the word "eat" had three meanings in a certain historical period: a. to put food in the mouth, chew, and swallow (the object of eating is solid), e.g., eat a peach; b. to drink (the object of eating is liquid), e.g., drink tea; c. to inhale (to inhale gas), e.g., smoke. However, in modern Chinese (Mandarin), "eat" only retains meaning a. The other two usages have been replaced by "drink" and "inhale." Because the emergence of "drink" and "inhale" affected the usage of "eat," "drink" and "inhale" are considered influencing words for "eat."

[0051] In this embodiment of the application, the acceptability of candidate words can be understood through the language confusion level, and then the influencing words that affect the development of the target word can be determined through the language confusion level of the candidate words, thereby achieving the purpose of determining which influencing words affect the development trajectory of language in the process of language development.

[0052] Figure 3 The diagram illustrates a flowchart of an exemplary embodiment of this application, showing how, for each candidate word, the perplexity of the target word and candidate words is determined based on M first target sentences containing the target word and M first candidate sentences containing the candidate words. Figure 2 Extending from the illustrated embodiment Figure 3 The embodiments shown are described in detail below. Figure 3 Examples and Figure 2 The differences between the embodiments and the similarities will not be repeated here.

[0053] like Figure 3As shown, for each candidate word, based on the M first target sentences containing the target word and the M first candidate sentences containing the candidate word, the language perplexity of the target word and the candidate word is determined, which may include the following steps.

[0054] Step S301: For each candidate word, replace the candidate word in the M first candidate sentences with the target word to obtain M second candidate sentences.

[0055] Step S302: Replace the target words in the M first target statements with candidate words to obtain M second target statements.

[0056] For example, the candidate words in the M first candidate statements are replaced with the target words, and the target words in the M first target statements are replaced with the candidate words to obtain the M second candidate statements and the M second target statements, so as to perform language perplexity calculation on the M second candidate statements and the M second target statements.

[0057] Step S303: Calculate the language perplexity of the M second candidate statements and the M second target statements respectively, and determine the language perplexity of the target word and the candidate word respectively.

[0058] Specifically, for each candidate word, M first candidate statements are given. After replacing the candidate words in the M first candidate statements with the target word to obtain M second candidate statements, the language perplexity of each of the M second candidate statements is calculated. The specific calculation method of the language perplexity of the second candidate statement is as follows: determine the string length of the second candidate statement, then use the language processing system to calculate the probability of the second candidate statement appearing, and finally use the string length of the second candidate statement and the probability of the second candidate statement appearing as parameters, and use the above formula (1) to calculate the language perplexity of the second candidate statement.

[0059] For example, since there are M candidate words and each candidate word has M first candidate statements, after replacing the candidate words in the first candidate statements with the target word, the number of second candidate statements is M*M. Therefore, the language perplexity of the target word is the sum of the perplexities of the M*M second candidate statements. After calculating the language perplexity of the M*M second candidate statements using the specific calculation method for the language perplexity of the second candidate statements described above, they are added together to obtain the language perplexity of the target word.

[0060] Specifically, for each candidate word, after replacing the target word in the M first target statements with the candidate word to obtain M second target statements, the language perplexity of each of the M second target statements will be calculated. The specific calculation method of the language perplexity of the second target statement is to determine the string length of the second target statement, then use the language processing system to calculate the probability of the second target statement appearing, and finally use the string length of the second target statement and the probability of the second target statement appearing as parameters, and use the above formula (1) to calculate to obtain the language perplexity of the second target statement.

[0061] For example, for each candidate word, the language perplexity of the candidate word is the sum of the perplexities of the M second target statements. After calculating the language perplexity of the M second target statements using the specific calculation method for the language perplexity of the second target statements described above, the results are added together to obtain the language perplexity of the candidate word.

[0062] In this embodiment of the application, a specific method for determining the perplexity of each of the M candidate words is introduced. By replacing the candidate words in the M first candidate sentences with the target words in the M first target sentences, M second candidate sentences and M second target sentences are obtained. The perplexity of the M second candidate sentences and M second target sentences is calculated to obtain the perplexity of each of the M candidate words.

[0063] Figure 4 The diagram shown is a flowchart illustrating a method for determining the influence words of language development according to another exemplary embodiment of this application. Figure 2 Extending from the illustrated embodiment Figure 4 The embodiments shown are described in detail below. Figure 4 Examples and Figure 2 The differences between the embodiments and the similarities will not be repeated here.

[0064] like Figure 4 As shown, before determining the language perplexity of the target word and the candidate word based on the M first target sentences containing the target word and the M first candidate sentences containing the candidate word for each candidate word, the following steps may also be included.

[0065] Step S401: Determine the language start and end corpus based on the start and end times of language development.

[0066] For example, the language start-end corpus records language information from the start time of language development to the end time of language development. For instance, if the start time of language development is the Tang Dynasty and the end time is the Qing Dynasty, all words that appeared from the Tang Dynasty to the Qing Dynasty, as well as the parts of speech and usage of the words, will be reflected in the language start-end corpus. It can be understood that the language start-end corpus is a dictionary within a time range.

[0067] For example, language information is extracted from a language corpus based on the start and end times of language development to obtain a language start-end corpus, which contains all language information from ancient times to the present.

[0068] Step S402: For each candidate word, based on the language start and end corpus, determine at least one first sentence containing the target word and at least one second sentence containing the candidate word.

[0069] Specifically, at least one first sentence containing the target word is determined based on a language start-end corpus. This means that all sentences containing the target word in the language start-end corpus are considered as at least one first sentence.

[0070] Specifically, at least one second sentence containing a candidate word is determined based on a language start-end corpus. This means that all sentences containing the candidate word in the language start-end corpus are considered as at least one second sentence.

[0071] Step S403: Calculate the language perplexity for at least one first statement and at least one second statement respectively, and determine M first target statements and M first candidate statements using a preset perplexity ranking threshold.

[0072] For example, based on the results of language confusion calculations for at least one first statement and at least one second statement, the at least one first statement and at least one second statement are sorted respectively, and M first statements and M second statements that meet a preset confusion ranking threshold are determined as the first target statement and the first candidate statement. The preset confusion ranking threshold can be the top M statements.

[0073] In this embodiment of the application, by using at least one first statement and at least one second statement whose language perplexity meets a preset perplexity ranking threshold as the first target statement and the first candidate statement, the interference of statements with low acceptability on the determination of influencing words is avoided.

[0074] Figure 5 The diagram illustrates a process in an exemplary embodiment of this application, where language perplexity calculations are performed on at least one first statement and at least one second statement, and M first target statements and M first candidate statements are determined using a preset perplexity ranking threshold. Figure 4 Extending from the illustrated embodiment Figure 5 The embodiments shown are described in detail below. Figure 5 Examples and Figure 4 The differences between the embodiments and the similarities will not be repeated here.

[0075] like Figure 5As shown, the perplexity of at least one first statement and at least one second statement is calculated respectively, and M first target statements and M first candidate statements are determined using a preset perplexity ranking threshold. This may include the following steps.

[0076] Step S501: Calculate the language perplexity of at least one first statement to obtain the language perplexity of each first statement.

[0077] Step S502: Based on the preset perplexity ranking threshold and the language perplexity of at least one first statement, determine M first target statements from at least one first statement.

[0078] For example, at least one first statement is subjected to language perplexity calculation to obtain the language perplexity of the target word in each first statement, and the M first statements that meet the preset perplexity ranking threshold and have the smallest language perplexity are selected as the first target statements.

[0079] Step S503: Calculate the language perplexity of at least one second statement to obtain the language perplexity of each second statement.

[0080] Step S504: Based on the preset perplexity ranking threshold and the language perplexity of at least one second statement, determine M first candidate statements from at least one second statement.

[0081] For example, at least one second statement is subjected to language perplexity calculation to obtain the language perplexity of the candidate word in each second statement, and M second statements that meet the preset perplexity ranking threshold and have the smallest language perplexity are selected as the first candidate statements, where M is a positive integer and the number of M can be determined according to the actual situation, which is not limited here.

[0082] In this embodiment of the application, a specific method is described for calculating the language perplexity of at least one first statement and at least one second statement respectively, and determining M first target statements and M first candidate statements. The perplexity of the first statement and the second statement is calculated respectively, and the obtained language perplexity is compared with a preset perplexity threshold. The first statement that meets the perplexity threshold requirement is the first target statement, and the first candidate statement that meets the perplexity threshold requirement is the first candidate statement.

[0083] Figure 6 The diagram illustrates a process for determining M candidate words corresponding to a target word based on the start time of language development, the end time of language development, and a preset word vector library, according to an exemplary embodiment of this application. Figures 2 to 5 Extending from the illustrated embodiment Figure 6 The embodiments shown are described in detail below. Figure 6 Examples and Figures 2 to 5The differences between the embodiments and the similarities will not be repeated here.

[0084] like Figure 6 As shown, determining M candidate words corresponding to a target word based on the start time of language development, the end time of language development, and a preset word vector library can include the following steps.

[0085] Step S601: Based on the preset word vector library, determine the target word vector corresponding to the target word.

[0086] For example, the target word vector is obtained from a preset word vector library mapping table. This preset word vector library mapping table represents the mapping relationship between word vectors and words. After the target word is determined, the word vector corresponding to the target word can be found in the preset word vector library mapping table. Among them, the target word vector is the word vector whose usage is closest to the target word.

[0087] Step S602: Determine the language start and end corpus based on the start and end times of language development.

[0088] Step S603: Based on the language start and end corpus and the preset word vector library, determine M candidate word vectors that match the target word vector.

[0089] For example, the M word vectors that are closest to the target word vector are determined as candidate word vectors using a language start-end corpus.

[0090] Step S604: Based on the M candidate word vectors, determine the M candidate words corresponding to the target word.

[0091] For example, if there is a mapping relationship between words and word vectors, then the corresponding candidate words can be determined by using M candidate word vectors.

[0092] In this embodiment of the application, a specific method for determining the M candidate words corresponding to the target word is introduced. First, the target word vector corresponding to the target word is determined. Then, the M word vectors that are closest to the target word vector are determined as candidate word vectors through the language start and end corpus. Finally, the M candidate words corresponding to the target word are determined through the M candidate word vectors.

[0093] Figure 7 The diagram illustrates a process for determining influencing words that affect the development of a target word based on the target word and the linguistic confusion level of each candidate word, according to an exemplary embodiment of this application. Figures 2 to 5 Extending from the illustrated embodiment Figure 7 The embodiments shown are described in detail below. Figure 7 Examples and Figures 2 to 5 The differences between the embodiments and the similarities will not be repeated here.

[0094] like Figure 7As shown, determining the influencing words that affect the development of the target word based on the target word and the linguistic perplexity of each candidate word can include the following steps.

[0095] Step S701: Based on the language perplexity of the target word and each candidate word, determine whether the target word and each candidate word meet the grammatical requirements using a preset perplexity threshold.

[0096] For example, each of the M candidate words has a language perplexity in the first candidate statement and a language perplexity in the second target statement. The language perplexity of each of the M candidate words is the sum of the language perplexities of the M candidate words in the first candidate statement and the M candidate words in the second target statement.

[0097] Specifically, a language confusion threshold is preset. Candidate words whose sum of language confusion meets the language confusion requirement are considered to meet the grammatical requirements and are used as starting words. There can be one or more candidate words that meet the language confusion requirement, that is, there can be one or more starting words. In the case of multiple starting words, the following steps can be performed on each of these multiple starting words.

[0098] Step S702: Take the target word and at least one word from each candidate word that meets the grammatical requirements as the starting word.

[0099] Step S703: For each starting word, identify at least one influencing statement that contains the starting word.

[0100] For example, a search is conducted in the language start-end corpus for all sentences containing the start word from the start time of language development to the end time of language development, and all sentences are treated as influencing sentences.

[0101] Step S704: Perform word segmentation on at least one influencing statement to determine at least one influencing word corresponding to at least one influencing statement.

[0102] For example, all influencing sentences are segmented into words, and the resulting words are input into a language processing system to obtain word vectors for each word. Then, all words in each word vector are considered as influencing words. Tokenization involves dividing the text string into a reasonable sequence of words. Tokenization can be performed using the jieba tokenizer or the tokenization module in the BERT model; no specific method is used here.

[0103] Step S705: Based on the attention mechanism, identify the influencing words that affect the development of the target word among at least one influencing word.

[0104] For example, through an attention mechanism, words that influence the usage of the starting word in the influencing sentence are calculated among all influencing words. Here, the attention mechanism can refer to attention that is purposeful, task-dependent, and actively and consciously focused on a certain object. In the embodiments of this application, the certain object can be the word that influences the usage of the starting word in the influencing sentence.

[0105] In this embodiment of the application, a specific method for determining the influencing words that affect the development of the target word is introduced. First, a word that meets the grammatical requirements is selected from the target word and each candidate word using a preset perplexity threshold as the starting word. Then, the influencing sentence containing the starting word is determined based on the starting word. Next, the influencing sentence is segmented to determine at least one influencing word corresponding to the influencing sentence. Finally, based on the attention mechanism, the influencing word that affects the development of the target word is determined from at least one influencing word.

[0106] Figure 8 The diagram shown is a flowchart illustrating a method for demonstrating the language development process provided in an exemplary embodiment of this application. Figure 8 As shown in the embodiments of this application, the method for demonstrating the language development process may include the following steps.

[0107] Step S801: In response to the user's input, trace back the development history of the target word and determine the influencing words that affect the development of the target word.

[0108] Specifically, using the above Figures 2 to 7 The method of any corresponding embodiment determines the influencing words that affect the development of the target word.

[0109] Step S802: Use a language processing system to determine the driving forces and mechanisms by which the influencing words affect the development of the target words.

[0110] For example, the driving forces and mechanisms of language development can be understood as the influencing factors that affect language development and the rules governing what kind of language will develop based on these influencing factors.

[0111] Step S803: Based on the driving forces and mechanisms by which influencing words affect the development of target words, the dynamic process of target word development is presented to users using the metaverse as a carrier.

[0112] Step S804: During the dynamic process of target word development, while adjusting the driving parameters, adjust the dynamic process of target word development based on the driving forces and mechanisms of influencing words on the development of target words.

[0113] For example, the motivation parameter is used to characterize the degree of influence of influencing factors on language development. Users can adjust the motivation parameter themselves. By adjusting the motivation parameter, the degree of influence of influencing factors on language development can be changed, so that language development is affected differently according to the degree of modification of the motivation parameter, resulting in different language development processes.

[0114] In this embodiment, by allowing the user to select the start time of language development, the end time of language development, and the target word for which the user wants to trace the development history, as well as by adjusting the driving parameters, the metaverse displays to the user the dynamic development process of the target word that changes with the adjustment of the driving parameters during the time period from the start time to the end time of language development.

[0115] Figure 9 The diagram shown is a structural schematic of a language development influence word determination device provided in an exemplary embodiment of this application. Figure 9 As shown, the language development influence word determination device provided in this application embodiment may include:

[0116] The acquisition module 901 is used to respond to the user's request to explore language development and to acquire the user's selected start time of language development, end time of language development, and target words for which the development history needs to be traced back.

[0117] The first determining module 902 is used to determine M candidate words corresponding to the target word based on the start time of language development, the end time of language development, and a preset word vector library, where M is a positive integer.

[0118] The second determining module 903 is used to determine the linguistic perplexity of the target word and the candidate word respectively, based on the M first target sentences containing the target word and the M first candidate sentences containing the candidate word, for each candidate word.

[0119] The third determination module 904 is used to determine the influencing words that affect the development of the target word based on the language perplexity of the target word and each candidate word.

[0120] In one embodiment of this application, the second determining module 903 is further configured to: for each candidate word, replace the candidate word in the M first candidate statements with the target word to obtain M second candidate statements; replace the target word in the M first target statements with the candidate word to obtain M second target statements; and calculate the language perplexity of the M second candidate statements and the M second target statements respectively to determine the language perplexity of the target word and the candidate word.

[0121] In one embodiment of this application, the language development influence word determination device further includes:

[0122] The fourth module is used to determine the language start and end corpus based on the start and end times of language development.

[0123] The fifth determination module is used to determine, for each candidate word, at least one first statement containing the target word and at least one second statement containing the candidate word, based on a language start-end corpus.

[0124] The sixth determination module is used to calculate the language perplexity of at least one first statement and at least one second statement respectively, and determine M first target statements and M first candidate statements using a preset perplexity ranking threshold.

[0125] In one embodiment of this application, the sixth determining module is further configured to calculate the language perplexity of at least one first statement respectively, so as to obtain the language perplexity of each of the at least one first statement;

[0126] Based on a preset perplexity ranking threshold and the perplexity of each of the at least one first statement, M first target statements are determined from the at least one first statement; the perplexity of each of the at least one second statement is calculated to obtain the perplexity of each of the at least one second statement; based on the preset perplexity ranking threshold and the perplexity of each of the at least one second statement, M first candidate statements are determined from the at least one second statement.

[0127] In one embodiment of this application, the first determining module 902 is further configured to: determine the target word vector corresponding to the target word based on a preset word vector library; determine the language start-end corpus based on the language development start time and language development end time; determine M candidate word vectors matching the target word vector based on the language start-end corpus and the preset word vector library; and determine M candidate words corresponding to the target word based on the M candidate word vectors.

[0128] In one embodiment of this application, the third determining module 904 is further configured to: determine whether the target word and each candidate word meet grammatical requirements based on their respective linguistic perplexity and using a preset perplexity threshold; take at least one word that meets the grammatical requirements among the target word and each candidate word as a starting word; for each starting word, determine at least one influencing statement containing the starting word; perform word segmentation on the at least one influencing statement to determine at least one influencing word corresponding to the at least one influencing statement; and, based on an attention mechanism, determine the influencing word that affects the development of the target word among the at least one influencing word.

[0129] It should be understood that Figure 9 The operation and function of the acquisition module 901, the first determination module 902, the second determination module 903, and the third determination module 904 in the provided language development influence word determination device can be referred to the above. Figures 2 to 7The methods for identifying words that influence language development are provided will not be elaborated upon here to avoid repetition.

[0130] Figure 10 The diagram shown is a schematic representation of a language development process demonstration device provided in an exemplary embodiment of this application. Figure 10 As shown, the language development influence word determination device provided in this application embodiment may include:

[0131] The first determining module 1001 is used to respond to the user's input request to trace the development history of the target word and determine the influencing words that affect the development of the target word.

[0132] For example, using the above Figure 9 The device for identifying words that influence the development of language is mentioned, and it identifies words that influence the development of target words.

[0133] The second determining module 1002 is used to determine the driving forces and mechanisms by which the influencing words affect the development of the target words using a language processing system.

[0134] For example, the motivation is used to characterize the factors influencing the development of the target word, and the mechanism is used to characterize the patterns influencing the development of the target word.

[0135] The display module 1003 is used to show users the dynamic process of the development of the target word based on the driving forces and mechanisms by which the influencing words affect the development of the target word, using the metaverse as a carrier.

[0136] The adjustment module 1004 is used to adjust the dynamic process of target word development based on the driving forces and mechanisms by which influencing words affect the development of target words if the user adjusts the driving force parameters during the dynamic process display of target word development.

[0137] For example, the motivation parameter is used to characterize the degree of influence of influencing factors on language development.

[0138] It should be understood that Figure 10 The operation and functions of the first determination module 1001, the second determination module 1002, and the process display module 1003 in the provided language development influence word determination device can be referred to the above. Figure 8 To avoid repetition, the methods for demonstrating the language development process provided will not be elaborated upon here.

[0139] Below, for reference Figure 11 This describes an electronic device according to embodiments of the present application. Figure 11 The diagram shown is a structural schematic of an electronic device provided in an exemplary embodiment of this application.

[0140] like Figure 11 As shown, the electronic device 110 includes one or more processors 1101 and memory 1102.

[0141] The processor 1101 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 110 to perform desired functions.

[0142] The memory 1102 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 1101 may execute the program instructions to implement the methods of the various embodiments of this application described above and / or other desired functions. The computer-readable storage medium may also store various contents such as word vector libraries, language start corpora, and language end corpora.

[0143] In one example, the electronic device 110 may also include an input device 1103 and an output device 1104, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0144] The input device 1103 may include, for example, a keyboard, a mouse, etc.

[0145] The output device 1104 can output various information to the outside, including word vector databases, language start corpora, and language end corpora. The output device 1104 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0146] Of course, for the sake of simplicity, Figure 11 Only some of the components of the electronic device 110 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 110 may include any other suitable components depending on the specific application.

[0147] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps of the methods described above according to various embodiments of this application.

[0148] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0149] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions that, when executed by a processor, cause the processor to perform the steps of the methods described above according to various embodiments of this application.

[0150] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0151] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0152] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0153] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0154] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0155] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for determining words that influence language development, characterized in that, include: In response to a user's request to explore language development, the system obtains the user's selected start time of language development, end time of language development, and target words for which the development history needs to be traced back. Based on the start time of the language development, the end time of the language development, and a preset word vector library, M candidate words corresponding to the target word are determined, where M is a positive integer. For each candidate word, based on M first target sentences containing the target word and M first candidate sentences containing the candidate word, the linguistic perplexity of the target word and the candidate word is determined respectively. Based on the target word and the language confusion level of each candidate word, words that meet the grammatical requirements are selected as starting words; For each starting word, identify the influencing statements that contain that starting word; Based on the attention mechanism, the influencing words that affect the development of the target word are determined from the word segments contained in the influencing statement.

2. The method according to claim 1, characterized in that, For each candidate word, determining the linguistic perplexity of the target word and the candidate words based on M first target sentences containing the target word and M first candidate sentences containing the candidate word includes: For each candidate word, replace the candidate word in the M first candidate statements with the target word to obtain M second candidate statements; The target words in the M first target statements are replaced with the candidate words to obtain M second target statements; The language perplexity of the M second candidate statements and the M second target statements is calculated respectively to determine the language perplexity of the target word and the candidate words.

3. The method according to claim 1, characterized in that, Before determining the language perplexity of the target word and the candidate words respectively based on M first target sentences containing the target word and M first candidate sentences containing the candidate words for each candidate word, the method further includes: Based on the start time and end time of the language development, a language start and end corpus is determined; For each candidate word, based on the language start-end corpus, at least one first statement containing the target word and at least one second statement containing the candidate word are determined; The language perplexity is calculated for the at least one first statement and the at least one second statement respectively, and the M first target statements and the M first candidate statements are determined using a preset perplexity ranking threshold.

4. The method according to claim 3, characterized in that, The step of calculating the language perplexity of the at least one first statement and the at least one second statement respectively, and determining the M first target statements and the M first candidate statements using a preset perplexity ranking threshold, includes: The language perplexity of each of the at least one first statement is calculated to obtain the language perplexity of each of the at least one first statement. Based on the preset perplexity ranking threshold and the language perplexity of each of the at least one first statement, the M first target statements are determined from the at least one first statement; The language perplexity of each of the at least one second statement is calculated to obtain the language perplexity of each of the at least one second statement. Based on the preset perplexity ranking threshold and the language perplexity of each of the at least one second statement, the M first candidate statements are determined from the at least one second statement.

5. The method according to any one of claims 1 to 4, characterized in that, The process of determining M candidate words corresponding to the target word based on the language development start time, the language development end time, and a preset word vector library includes: Based on the preset word vector library, determine the target word vector corresponding to the target word; Based on the start time and end time of the language development, a language start and end corpus is determined; Based on the language start and end corpus and the preset word vector library, M candidate word vectors matching the target word vector are determined; Based on the M candidate word vectors, determine the M candidate words corresponding to the target word.

6. The method according to any one of claims 1 to 4, characterized in that, The process of selecting words that meet grammatical requirements as starting words based on the target word and the linguistic confusion level of each candidate word includes: Based on the language perplexity of the target word and each candidate word, a preset perplexity threshold is used to determine whether the target word and each candidate word meet the grammatical requirements; The target word and at least one word from each candidate word that meets the grammatical requirements are used as the starting word; The attention-based mechanism for determining influencing words that affect the development of the target word from the word segments contained in the influencing statement includes: Perform word segmentation on the at least one influencing statement to determine at least one influencing word corresponding to the at least one influencing statement; Based on the attention mechanism, among the at least one influencing word, the influencing word that affects the development of the target word is identified.

7. A method for demonstrating the process of language development, characterized in that, include: In response to user input requiring a target word to trace its development history, the method described in any one of claims 1 to 6 is used to determine the influencing words that affect the development of the target word; A language processing system is used to determine the motivations and mechanisms by which the influencing words affect the development of the target words; wherein, the motivations are used to characterize the influencing factors affecting the development of the target words, and the mechanisms are used to characterize the patterns affecting the development of the target words; Based on the driving forces and mechanisms by which the influencing words affect the development of the target words, the dynamic process of the development of the target words is presented to users using the metaverse as a carrier. If the user adjusts the driving parameters during the dynamic process of the target word's development, the dynamic process of the target word's development will be adjusted based on the driving forces and mechanisms by which the influencing words affect the development of the target word. The driving parameters are used to characterize the degree of influence of the influencing factors on the development of the target word.

8. A device for determining words that influence language development, characterized in that, include: The acquisition module is used to respond to a user's request to explore language development by acquiring the user's selected start time of language development, end time of language development, and target words for which the development history needs to be traced back. The first determining module is used to determine M candidate words corresponding to the target word based on the start time of the language development, the end time of the language development, and a preset word vector library, where M is a positive integer. The second determining module is used to determine the language perplexity of the target word and the candidate word respectively, based on M first target sentences containing the target word and M first candidate sentences containing the candidate word, for each candidate word; The third determining module is used to select words that meet the grammatical requirements as starting words based on the target word and the language confusion degree of each candidate word. For each starting word, identify the influencing statements containing the starting word; based on an attention mechanism, identify the influencing words that affect the development of the target word from the word segments contained in the influencing statements.

9. A device for demonstrating the process of language development, characterized in that, include: The first determining module is used to determine the influencing words that affect the development of the target word in response to the user's input of the need to trace the development history of the target word, using the method described in any one of claims 1 to 6. The second determining module is used to determine the motivation and mechanism by which the influencing word affects the development of the target word using a language processing system; wherein, the motivation is used to characterize the influencing factors affecting the development of the target word, and the mechanism is used to characterize the pattern affecting the development of the target word; The display module is used to present the dynamic process of the development of the target word to the user based on the motivation and mechanism by which the influencing words affect the development of the target word, using the metaverse as a carrier. The adjustment module is used to adjust the dynamic process of the target word's development based on the driving forces and mechanisms by which the influencing words affect the development of the target word if the user adjusts the driving force parameters during the dynamic process display of the target word's development. The driving force parameters are used to characterize the degree of influence of the influencing factors on the development of the target word.

10. A computing device, characterized in that, This includes processing components and storage components; The storage component stores one or more computer instructions; the one or more computer instructions are to be invoked and executed by the processing component to implement the method as described in any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for performing the method described in any one of claims 1 to 7.

Images