CN113657110A - Information processing method and device and electronic equipment - Google Patents
Information processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN113657110A CN113657110A CN202110915000.4A CN202110915000A CN113657110A CN 113657110 A CN113657110 A CN 113657110A CN 202110915000 A CN202110915000 A CN 202110915000A CN 113657110 A CN113657110 A CN 113657110A
- Authority
- CN
- China
- Prior art keywords
- word slot
- target
- word
- slot
- target user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 42
- 238000003672 processing method Methods 0.000 title claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 79
- 238000004458 analytical method Methods 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 8
- 238000012360 testing method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000003058 natural language processing Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
Abstract
The disclosure discloses an information processing method, an information processing device and electronic equipment, and relates to the technical field of artificial intelligence such as automatic driving, voice technology and internet of vehicles. The specific implementation scheme is as follows: when determining the attention of the user to the multidimensional attribute of the vehicle, the dialogue content of the target user for a preset object can be obtained first, the dialogue content is subjected to word slot analysis processing, and a word slot corresponding to the target user and a word frequency corresponding to the word slot are determined according to an analysis result; and then, the word slot corresponding to the target user and the word frequency corresponding to the word slot are input into the prediction model, and the attention of the target user to the multi-dimensional attribute of the preset object is determined by means of the prediction model, so that the determination efficiency of the prediction result is improved, and the accuracy of the prediction result is improved.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to an information processing method and apparatus, and an electronic device, and in particular, to the technical fields of automated driving, voice technology, and artificial intelligence such as internet of vehicles.
Background
The method has the advantages that the attention degree of the client to the multidimensional attributes of the vehicle is determined, and the important role is played in assisting the vehicle enterprise to make a sales strategy or improving the interior of the vehicle enterprise by self. In the prior art, when determining the attention of a customer to the multidimensional attribute of a vehicle, a salesperson mainly collects the requirements of different driver test customers through a manual conversation mode and arranges the requirements, and then predicts the attention of the customer to the multidimensional attribute of the vehicle based on the arranged information.
However, predicting the attention of the customer to the multidimensional attribute of the vehicle in a manual manner may result in low accuracy of the prediction result due to personal subjectivity.
Disclosure of Invention
The invention provides an information processing method, an information processing device and electronic equipment, which improve the accuracy of a prediction result when predicting the attention of a user to multidimensional attributes of a vehicle.
According to a first aspect of the present disclosure, there is provided an information processing method, which may include:
and acquiring the conversation content of the target user aiming at the preset object.
And performing word slot analysis processing on the conversation content, and determining a word slot corresponding to the target user and a word frequency corresponding to the word slot according to an analysis result.
And inputting the word slot corresponding to the target user and the word frequency corresponding to the word slot into a prediction model to obtain the attention of the target user to the multi-dimensional attribute of the preset object.
According to a second aspect of the present disclosure, there is provided an information processing apparatus, which may include:
and the acquisition unit is used for acquiring the conversation content of the target user aiming at the preset object.
And the processing unit is used for carrying out word slot analysis processing on the conversation content and determining a word slot corresponding to the target user and a word frequency corresponding to the word slot according to an analysis result.
And the prediction unit is used for inputting the word slot corresponding to the target user and the word frequency corresponding to the word slot into a prediction model to obtain the attention of the target user to the multi-dimensional attribute of the preset object.
According to a third aspect of the present disclosure, there is provided an electronic device, which may include:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the information processing method of the first aspect.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the information processing method of the first aspect described above.
According to a fifth aspect of the present disclosure, there is provided a computer program product comprising: a computer program stored in a readable storage medium, from which at least one processor of an electronic device can read the computer program, the at least one processor executing the computer program causing the electronic device to execute the information processing method according to the first aspect described above.
According to the technical scheme, when the attention degree of the user to the multidimensional attribute of the vehicle is predicted, the accuracy of the prediction result is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
fig. 1 is a schematic flow chart of an information processing method provided according to a first embodiment of the present disclosure;
fig. 2 is a schematic flow chart of an information processing method provided according to a second embodiment of the present disclosure;
fig. 3 is a flowchart illustrating an information processing method according to a third embodiment of the present disclosure;
fig. 4 is a flowchart schematically illustrating an information processing apparatus provided according to a fourth embodiment of the present disclosure;
fig. 5 is a schematic block diagram of an electronic device provided by an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
In embodiments of the present disclosure, "at least one" means one or more, "a plurality" means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone, wherein A and B can be singular or plural. In the description of the text of the present disclosure, the character "/" generally indicates that the former and latter associated objects are in an "or" relationship. In addition, in the embodiments of the present disclosure, "first", "second", "third", "fourth", "fifth", and "sixth" are only used to distinguish the contents of different objects, and have no other special meaning.
The technical scheme provided by the embodiment of the disclosure can be applied to the field of product sales. Taking the field of automobile sales as an example, if a vehicle enterprise can master the attention of a user to the multidimensional attribute of the vehicle in advance, and the preference of the user to the vehicle is analyzed through the attention of the user to the multidimensional attribute of the vehicle, a suitable target vehicle is formulated for the user based on the preference of the user, and the target vehicle is recommended to the user, so that the success rate of vehicle sales can be effectively improved.
In the related technology, when the attention of a user to the multidimensional attribute of the vehicle is determined, mainly, a salesperson collects the requirements of different driver test users in a manual conversation mode and arranges the requirements, and then the attention of the customer to the multidimensional attribute of the vehicle is predicted based on the arranged information. However, predicting the attention of the customer to the multidimensional attribute of the vehicle in a manual manner may result in low accuracy of the prediction result due to personal subjectivity.
In order to solve the problem that the accuracy of a prediction result is low due to personal subjectivity and improve the accuracy of the prediction result, when the attention of a user to a vehicle multidimensional attribute is determined, after conversation content of a target user for a preset object is obtained, word slot analysis processing can be performed on the conversation content, and a word slot corresponding to the target user and a word frequency corresponding to the word slot are determined according to an analysis result; and then, the word slot corresponding to the target user and the word frequency corresponding to the word slot are input into the prediction model, and the attention of the target user to the multi-dimensional attribute of the preset object is determined by means of the prediction model, so that the determination efficiency of the prediction result is improved, and the accuracy of the prediction result is improved.
Based on the above technical concept, embodiments of the present disclosure provide an information processing method, which will be described in detail below with specific embodiments. It is to be understood that the following detailed description may be combined with other embodiments, and that the same or similar concepts or processes may not be repeated in some embodiments.
Example one
Fig. 1 is a flowchart illustrating an information processing method according to a first embodiment of the present disclosure, which may be performed by software and/or a hardware device, for example, a terminal or a server. For example, referring to fig. 1, the information processing method may include:
s101, obtaining conversation content of a target user aiming at a preset object.
For example, when obtaining the dialog content of the target user for the preset object, the dialog content of the target user for the preset object may be obtained from another terminal, or the dialog content of the target user for the preset object may be obtained locally, and may be specifically set according to actual needs.
Taking a preset object as a vehicle as an example, the dialog content of the target user for the preset object can be acquired from the vehicle terminal in a network request manner such as http. The implementation process can include: the basic information of the target user is input through an app or Erp system of an enterprise to which the vehicle belongs, and the identity of the target user, such as the name, the identity card number or the telephone number of the target user, is generated, so long as the target user can be uniquely identified. When the pilot ride and test drive vehicle is started, voice monitoring service in the vehicle can be started together, dialogue voice data of a target user and a salesperson for the vehicle are collected through the voice monitoring service, audio hardware and software in the vehicle are adopted to distinguish the dialogue contents, the voice data of the target user for the vehicle are extracted from the dialogue contents, voice recognition is carried out on the voice data of the target user for the vehicle, dialogue contents of the target user for a preset object are obtained, the dialogue contents are in a text form, and the dialogue contents are sent to an information processing device through network requests such as http and the like, so that the information processing device can obtain the dialogue contents of the target user for the preset object from a vehicle terminal through network requests such as http and the like.
After obtaining the dialog content of the target user for the preset object, performing word slot parsing processing on the dialog content, and determining a word slot corresponding to the target user and a word frequency corresponding to the word slot according to a parsing result, that is, executing the following S102:
and S102, carrying out word slot analysis processing on the conversation content, and determining a word slot corresponding to the target user and a word frequency corresponding to the word slot according to an analysis result.
The word frequency refers to the frequency of occurrence of a given word slot in the dialog content, and can be used as an important index for reflecting the attention of the user to the multidimensional attribute of the preset object, so that the attention of the user to the multidimensional attribute of the preset object can be reflected more accurately by counting the word frequency corresponding to the word slot and using the word slot and the word frequency corresponding to the word slot as the input value of the prediction model, and the accuracy of the prediction result can be further improved.
For example, when parsing the word slot parsing processing is performed on the dialog content, if the parsing result of a certain statement or dialog segment in the dialog content does not include a word slot associated with the preset object, it may be understood that the word slot associated with the preset object is not parsed, and the statement or dialog segment may be directly discarded; and if the analysis result of a certain sentence or conversation fragment in the conversation content comprises a word slot associated with the preset object, determining a word slot corresponding to the target user and a word frequency corresponding to the word slot according to the analyzed word slot associated with the preset object.
Continuing to take the preset object as an example of the vehicle, the word slot associated with the vehicle may include a head space, noise, a steering wheel, power, and the like, and may be specifically set according to actual needs. For example, the word frequency corresponding to the head space may be 5 times, the word frequency corresponding to the noise may be 3 times, the word frequency corresponding to the steering wheel may be 1 time, and the word frequency corresponding to the power may be 2 times, which may be specifically set according to actual needs.
After determining the word slot corresponding to the target user and the word frequency corresponding to the word slot according to the parsing result, the following S103 may be performed:
s103, inputting the word slot corresponding to the target user and the word frequency corresponding to the word slot into the prediction model to obtain the attention of the target user to the multi-dimensional attribute of the preset object.
The prediction model is obtained by training in a mode of manual labeling in advance and by utilizing a machine learning algorithm which is mature at present. The input of the prediction model is a word slot and a corresponding word frequency, and the output is the attention of a target user to the multi-dimensional attribute of the preset object.
For example, the number of word slots may be 1, or may be multiple, and may be specifically set according to actual needs. In general, the more the number of word slots is, the more accurate the word frequency corresponding to each word slot is counted, and the more accurate the result of the attention of the user to the multi-dimensional attribute of the preset object is obtained through the prediction model.
Continuing to take the preset object as an example, assuming that the word slots corresponding to the target user respectively include: head space, noise, steering wheel, the word frequency that each word groove corresponds respectively is: 5 times, 3 times, 1 time; after the 3 word slots corresponding to the target user and the respective word frequencies corresponding to the 3 word slots are input to the prediction model, the attention of the target user to the multi-dimensional attribute of the preset object can be obtained, for example, the space: 90. comfort: 80. power: 50. in this case, the multi-dimensional attributes include three dimensions of space, comfort, and power, where the focus of the space dimension is 90, the focus of the comfort dimension is 80, and the focus of the power dimension is 50, indicating that the target user is more focused on the space and comfort of the vehicle than the power of the vehicle.
It should be noted that the embodiment of the present disclosure is described only by using three dimensions, including space, comfort and power, of the multidimensional attribute, in an actual application scenario, the dimension of the multidimensional attribute is not limited to the three dimensions, and the dimension may be extended to more dimension attributes as the prediction model is updated and iterated.
It can be seen that, in the embodiment of the present disclosure, when determining the attention of the user to the multidimensional attribute of the vehicle, the dialog content of the target user for the preset object may be obtained first, the dialog content is subjected to word slot analysis, and the word slot corresponding to the target user and the word frequency corresponding to the word slot are determined according to the analysis result; and then, the word slot corresponding to the target user and the word frequency corresponding to the word slot are input into the prediction model, and the attention of the target user to the multi-dimensional attribute of the preset object is determined by means of the prediction model, so that the determination efficiency of the prediction result is improved, and the accuracy of the prediction result is improved.
Based on the embodiment shown in fig. 1, since the obtained dialog content of the target user for the preset object usually includes some statements that do not relate to the preset object, for example, some other chatting statements are inserted in the dialog process, and the other chatting statements have no reference meaning for determining the attention of the target user to the multidimensional attribute of the preset object, in order to avoid continuing to perform subsequent processing on the other chatting statements, the obtained dialog content of the target user for the preset object may be first screened, so that only the screened statements that relate to the preset object may be subsequently subjected to word-slot parsing processing, and the implementation process of the word-slot parsing processing may be referred to as an embodiment two shown in fig. 2 below.
Example two
Fig. 2 is a flowchart illustrating an information processing method according to a second embodiment of the present disclosure, which may also be performed by software and/or hardware devices. For example, referring to fig. 2, the information processing method may include:
s201, scoring is carried out on each statement in the dialogue content, and a score value corresponding to each statement is obtained.
For example, when scoring is performed on each statement in the dialog content, a target vertical class matching a preset object may be determined from a natural language understanding (NLP) library according to the preset object; scoring each sentence in the dialogue content according to the target vertical class to obtain a score value corresponding to each sentence; the statements in the dialog content may be scored in other manners, and the embodiments of the present disclosure are only described as examples of scoring the statements in the dialog content according to the target vertical category, but the embodiments of the present disclosure are not limited to this.
Natural language processing is a technology for communicating with a computer by using natural language, and because the key to processing natural language is to let the computer "understand" natural language, natural language processing is also called Natural Language Understanding (NLU) or computational linguistics (computational linguistics).
Taking a preset object as an example, when scoring is performed on each sentence in the dialogue content of the vehicle by the target user, considering that the natural language understanding library includes a plurality of verticals applicable to different services, a tentative riding and test driving verticals matched with the vehicle can be determined from the natural language understanding library, and scoring is performed on each sentence in the dialogue content through the tentative riding and test driving verticals, so that a score value corresponding to each sentence is obtained. It should be noted that how to score each sentence in the dialog content through the tentative riding and trial riding verticals can be referred to the related description, and here, the embodiment of the present disclosure is not described again.
S202, performing word slot analysis processing on the target sentences with the score values larger than a preset threshold value according to the score values corresponding to the sentences.
The value of the preset threshold may be set according to actual needs, and the embodiment of the present disclosure is not particularly limited to the value of the preset threshold. The number of the target sentences may also be 1, or may also be multiple, and may be specifically set according to actual needs, where the number of the target sentences is not specifically limited in the embodiments of the present disclosure.
In general, the higher the score value of a sentence is, the higher the association degree between the word slot included in the sentence and the preset object is; conversely, the lower the score value of a sentence, the lower the association degree of the word slot included in the sentence with the preset object.
For example, if the preset object is a vehicle, and the dialog content of the target user for the vehicle includes "the head space is insufficient and the noise is too large, … … we want to drive to the XX area, but the recent weather is too hot", then by scoring each sentence, the score values of the sentences such as "the head space is insufficient" and the noise is too large "can be obtained, which is higher than the score value of the sentence" we want to drive to the XX area ", and the score value of the sentence" we want to drive to the XX area "is higher than the score value of the sentence" the recent weather is too hot ". For example, through the score values of the sentences, the sentences of "the head space of the vehicle is insufficient", "the noise is too large", and "we want to drive to the XX area" in the conversation content can be used as target sentences to perform word slot analysis processing; the sentence "however, the weather is too hot recently" is a chatty sentence; or, the sentence "we want to drive to the XX area" may be understood as a chatting sentence, which may be specifically set according to actual needs, and the word slot processing is not performed on the chatting sentence, so that the data amount required to perform the word slot parsing processing may be reduced, and the word slot parsing efficiency is effectively improved.
It is to be understood that, if the reduction of the data amount required to be subjected to the word slot analysis processing is not considered, the word slot analysis processing may be directly performed on each sentence in the dialog content, and the embodiment of the present disclosure is only described by taking the example of performing the word slot analysis processing on the target sentence with the score value greater than the preset threshold, but the embodiment of the present disclosure is not limited thereto.
It can be seen that, in the embodiment of the present disclosure, when performing word slot parsing on a dialog content of a preset object by a target user, scoring may be performed on each sentence in the dialog content to obtain a score value corresponding to each sentence, and according to the score value corresponding to each sentence, performing word slot parsing on a target sentence whose score value is greater than a preset threshold, so that by scoring each sentence, a target sentence with a higher association degree with the preset object may be screened out from the dialog content through the score value, and only a target sentence with a higher association degree with the preset object is subjected to word slot parsing, which reduces a data amount that needs to be subjected to word slot parsing, thereby effectively improving word slot parsing efficiency.
Based on the embodiment shown in fig. 1 or fig. 2, after the word slot analysis processing is performed on the dialog content, a word slot with a high degree of association with the preset object included in the dialog content may be obtained. The target word slot can be understood as a word slot with a higher degree of association with the preset object, and is subsequently helpful for determining the attention of the user to the multidimensional attribute of the preset object. If the preset object is a vehicle, the target word slot may include a head space, noise, a steering wheel, and the like. If the predetermined object is a computer, the target word slot may include memory, size, noise, etc.
Thus, after the target word slot is analyzed, the word slot corresponding to the target user and the word frequency corresponding to the word slot can be determined according to the analyzed target word slot. In order to facilitate understanding of how to determine the word slot corresponding to the target user and the word frequency corresponding to the word slot according to the parsed target word slot in the embodiment of the present disclosure, the following will be described in detail through the embodiment shown in fig. 3.
EXAMPLE III
Fig. 3 is a flowchart illustrating an information processing method according to a third embodiment of the present disclosure, which may also be performed by software and/or hardware devices. For example, referring to fig. 3, the information processing method may include:
s301, judging whether the word slot library corresponding to the target user comprises the target word slot.
For a certain user, if the word slot analyzed according to the dialog content of the user once and the word frequency corresponding to the word slot are only used for predicting the attention of the user to the multidimensional attribute of the preset object, the accuracy of the prediction result may not be guaranteed generally because the number of the word slots is small or the number of the corresponding frequency is small, so that in a general situation, for each user, an enterprise to which the preset object belongs may be correspondingly provided with a word slot library corresponding to the user, and the word slot library may be a word slot library formed by performing word slot analysis processing on the acquired dialog content of the user through multiple ways. The word slot library not only comprises word slots corresponding to the users, but also comprises word frequencies corresponding to the word slots.
Therefore, after the target word slot included in the conversation content is analyzed, the word slot corresponding to the target user and the word frequency corresponding to the word slot can be determined together by combining the word slot library corresponding to the target user, and the accuracy of the prediction result can be further improved.
It can be understood that if the content of the current session is longer, the analyzed target word slot is enough for predicting the attention of the target user to the multi-dimensional attribute of the preset object; or the target user does not establish a corresponding word slot library before, or the attention of the user to the multi-dimensional attribute of the preset object can be predicted only according to the target word slot analyzed from the content of the current conversation and the word frequency corresponding to the target word slot. Here, the embodiment of the present disclosure is described by taking an example of jointly determining a word slot corresponding to a target user and a word frequency corresponding to the word slot by combining a word slot library corresponding to the target user, but the embodiment of the present disclosure is not limited thereto.
When the word slot corresponding to the target user and the word frequency corresponding to the word slot are determined together by combining the word slot library corresponding to the target user, it may be determined whether the word slot library corresponding to the target user includes the target word slot or not, if the word slot library includes the target word slot, the following S302 is performed, and if the word slot library does not include the target word slot, the following S303 is performed.
S302, if the target word slot is included, the word frequency corresponding to the target word slot in the word slot library is updated, and the word slot corresponding to the target user and the word frequency corresponding to the word slot are determined based on the updated word slot library.
When the target word slot corresponding to the target user already comprises the target word slot analyzed this time, it is indicated that the target word slot is already recorded in the word slot library. For example, when the word frequency corresponding to the target word slot recorded in the word slot library is updated, a preset value may be added to the word frequency corresponding to the target word slot, so as to update the word frequency corresponding to the target word slot, and thus, the word slot in the word slot library may be determined as the word slot corresponding to the target user, and the word frequency after the update of the target word slot may be determined as the word frequency corresponding to the target word slot, so as to determine the word slot corresponding to the target user and the word frequency corresponding to the word slot. In general, the preset value may be set to 1, but is not limited to 1.
S303, if the target word slot is not included, setting the word frequency corresponding to the target word slot, and determining the word slot corresponding to the target user and the word frequency corresponding to the word slot according to the target word slot, the word frequency corresponding to the target word slot and the word slot library.
When the target word slot corresponding to the target user does not include the target word slot analyzed this time, in such a case, the word frequency corresponding to the target word slot may be set first, and in a general case, the word frequency corresponding to the target word slot may be set to 1, but is not limited to 1; and determining the target word slot and all the word slots in the word slot library as the word slots corresponding to the target user, determining the word frequency corresponding to the set target word slot as the word frequency corresponding to the target word slot, and keeping the word frequency corresponding to the word slots in the word slot library unchanged, thereby determining the word slots corresponding to the target user and the word frequency corresponding to the word slots.
It can be understood that, under the circumstance, if the word slot library does not include the target word slot, the target word slot and the word frequency corresponding to the target word slot may be added to the word slot library corresponding to the target user, so as to update the word slot library corresponding to the target user, so that the word slot included in the word slot library and the word frequency corresponding to the word slot are more accurate and complete, and the attention of the target user to the multi-dimensional attribute of the preset object is determined again based on the updated word slot library.
It can be seen that, in the embodiment of the present disclosure, when determining the word slot corresponding to the target user and the word frequency corresponding to the word slot according to the result, it may be determined whether the word slot library corresponding to the target user includes the target word slot; if the target word slot is included, updating the word frequency corresponding to the target word slot in the word slot library, and determining the word slot corresponding to the target user and the word frequency corresponding to the word slot based on the updated word slot library; if the target word slot is not included, setting the word frequency corresponding to the target word slot, and determining the word slot corresponding to the target user and the word frequency corresponding to the word slot according to the target word slot, the word frequency corresponding to the target word slot and the word slot library; therefore, on the basis of the analysis result of the conversation content, the word slot corresponding to the target user and the word frequency corresponding to the word slot are determined together by combining the word slot library corresponding to the target user, the word slot and the word frequency corresponding to the word slot are considered to be more perfect, and the accuracy of the prediction result can be further improved.
Based on any one of the above embodiments, after the attention degree of the target user to the preset object multi-dimensional attribute is determined by means of the prediction model, the attention degree of the target user to the preset object multi-dimensional attribute can be determined to be presented through various internet forms such as APP, Erp and the like, and an enterprise can conveniently master the attention degree of the target user to the preset object multi-dimensional attribute at any time.
In addition, a target object matched with the attention degree of the multi-dimensional attributes can be further determined from the preset object library according to the attention degree of the target user to the multi-dimensional attributes of the preset object; and sending the information of the target object to the client of the target user, so that a suitable target object is formulated for the target user based on the preference of the target user, and the suitable target object is recommended to the target user, thereby effectively improving the selling success rate of the target object.
Example four
Fig. 4 is a schematic flowchart of an information processing apparatus 40 according to a fourth embodiment of the present disclosure, and for example, referring to fig. 4, the information processing apparatus 40 may include:
an obtaining unit 401, configured to obtain a dialog content of a target user for a preset object.
And the processing unit 402 is configured to perform word slot parsing on the dialog content, and determine a word slot corresponding to the target user and a word frequency corresponding to the word slot according to a parsing result.
The predicting unit 403 is configured to input the word slot corresponding to the target user and the word frequency corresponding to the word slot into the prediction model, so as to obtain the attention of the target user to the multi-dimensional attribute of the preset object.
Optionally, the parsing result includes a target word slot, and the processing unit 402 includes a first processing module, a second processing module, and a third processing module.
And the first processing module is used for judging whether the word slot library corresponding to the target user comprises the target word slot.
And the second processing module is used for updating the word frequency corresponding to the target word slot in the word slot library if the target word slot is included, and determining the word slot corresponding to the target user and the word frequency corresponding to the word slot based on the updated word slot library.
And the third processing module is used for setting the word frequency corresponding to the target word slot if the target word slot is not included, and determining the word slot corresponding to the target user and the word frequency corresponding to the word slot according to the target word slot, the word frequency corresponding to the target word slot and the word slot library.
Optionally, the processing unit 402 further comprises a fourth processing module.
And the fourth processing module is used for adding the target word slot and the word frequency corresponding to the target word slot into the word slot library if the target word slot is not included.
Optionally, the processing module further comprises a fifth processing module and a sixth processing module.
And the fifth processing module is used for scoring each statement in the dialogue content to obtain the score value corresponding to each statement.
And the sixth processing module is used for carrying out word slot analysis processing on the target sentences with the score values larger than the preset threshold value according to the score values corresponding to the sentences.
Optionally, the fifth processing module comprises a first processing sub-module and a second processing sub-module.
And the first processing submodule is used for determining a target vertical class matched with the preset object from the natural language understanding library according to the preset object.
And the second processing submodule is used for scoring each statement in the dialogue content according to the target vertical class to obtain a score value corresponding to each statement.
Optionally, the information processing apparatus 40 further includes a determination unit and a transmission unit.
And the determining unit is used for determining the target object matched with the attention degree of the multi-dimensional attributes from the preset object library according to the attention degree of the target user to the multi-dimensional attributes of the preset object.
And the sending unit is used for sending the information of the target object to the client of the target user.
The information processing apparatus 40 provided in the embodiment of the present disclosure may execute the technical solution of the information processing method shown in any one of the above embodiments, and the implementation principle and the beneficial effect of the information processing method are similar to those of the information processing method, and reference may be made to the implementation principle and the beneficial effect of the information processing method, which are not described herein again.
In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
According to an embodiment of the present disclosure, the present disclosure also provides a computer program product comprising: a computer program, stored in a readable storage medium, from which at least one processor of the electronic device can read the computer program, the at least one processor executing the computer program causing the electronic device to perform the solution provided by any of the embodiments described above.
Fig. 5 is a schematic block diagram of an electronic device 50 provided by an embodiment of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 5, the apparatus 50 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)502 or a computer program loaded from a storage unit 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 50 can also be stored. The calculation unit 501, the ROM 502, and the RAM 503 are connected to each other by a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
A number of components in device 50 are connected to I/O interface 505, including: an input unit 506 such as a keyboard, a mouse, or the like; an output unit 507 such as various types of displays, speakers, and the like; a storage unit 508, such as a magnetic disk, optical disk, or the like; and a communication unit 509 such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows the device 50 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The computing unit 501 may be a variety of general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 501 executes the respective methods and processes described above, such as the information processing method. For example, in some embodiments, the information processing method may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 50 via ROM 502 and/or communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the information processing method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the information processing method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server can be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (15)
1. An information processing method comprising:
acquiring conversation content of a target user aiming at a preset object;
performing word slot analysis processing on the conversation content, and determining a word slot corresponding to the target user and a word frequency corresponding to the word slot according to an analysis result;
and inputting the word slot corresponding to the target user and the word frequency corresponding to the word slot into a prediction model to obtain the attention of the target user to the multi-dimensional attribute of the preset object.
2. The method of claim 1, wherein the parsing result includes a target word slot, and determining the word slot corresponding to the target user and the word frequency corresponding to the word slot according to the parsing result comprises:
judging whether the word slot library corresponding to the target user comprises the target word slot or not;
if the target word slot is included, updating the word frequency corresponding to the target word slot in the word slot library, and determining the word slot corresponding to the target user and the word frequency corresponding to the word slot based on the updated word slot library;
and if the target word slot is not included, setting the word frequency corresponding to the target word slot, and determining the word slot corresponding to the target user and the word frequency corresponding to the word slot according to the target word slot, the word frequency corresponding to the target word slot and the word slot library.
3. The method of claim 2, further comprising:
and if the target word slot is not included, adding the target word slot and the word frequency corresponding to the target word slot into the word slot library.
4. The method according to any one of claims 1-3, wherein the performing a word-slot parsing process on the dialog content comprises:
scoring each sentence in the conversation content to obtain a score value corresponding to each sentence;
and performing word slot analysis processing on the target sentences with the score values larger than a preset threshold value according to the score values corresponding to the sentences.
5. The method of claim 4, wherein the scoring each sentence in the dialog content to obtain a score value corresponding to each sentence comprises:
according to the preset object, determining a target vertical class matched with the preset object from a natural language understanding library;
and scoring each sentence in the conversation content according to the target vertical category to obtain a score value corresponding to each sentence.
6. The method of any of claims 1-5, wherein the method further comprises:
determining a target object matched with the attention degree of the multi-dimensional attribute from a preset object library according to the attention degree of the target user to the multi-dimensional attribute of the preset object;
and sending the information of the target object to the client of the target user.
7. An information processing apparatus comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring the conversation content of a target user aiming at a preset object;
the processing unit is used for carrying out word slot analysis processing on the conversation content and determining a word slot corresponding to the target user and a word frequency corresponding to the word slot according to an analysis result;
and the prediction unit is used for inputting the word slot corresponding to the target user and the word frequency corresponding to the word slot into a prediction model to obtain the attention of the target user to the multi-dimensional attribute of the preset object.
8. The apparatus of claim 7, wherein the parsing result comprises a target word slot, and the processing unit comprises a first processing module, a second processing module, and a third processing module;
the first processing module is configured to determine whether the word slot library corresponding to the target user includes the target word slot;
the second processing module is configured to update the word frequency corresponding to the target word slot in the word slot library if the target word slot is included, and determine the word slot corresponding to the target user and the word frequency corresponding to the word slot based on the updated word slot library;
and the third processing module is configured to set a word frequency corresponding to the target word slot if the target word slot is not included, and determine the word slot corresponding to the target user and the word frequency corresponding to the word slot according to the target word slot, the word frequency corresponding to the target word slot and the word slot library.
9. The apparatus of claim 8, the processing unit further comprising a fourth processing module;
and the fourth processing module is configured to add the target word slot and the word frequency corresponding to the target word slot in the word slot library if the target word slot is not included.
10. The apparatus of any of claims 7-9, wherein the processing module further comprises a fifth processing module and a sixth processing module;
the fifth processing module is configured to score each sentence in the dialog content to obtain a score value corresponding to each sentence;
and the sixth processing module is used for performing word slot analysis processing on the target sentences with the score values larger than a preset threshold value according to the score values corresponding to the sentences.
11. The apparatus of claim 10, wherein the fifth processing module comprises a first processing sub-module and a second processing sub-module;
the first processing submodule is used for determining a target vertical class matched with the preset object from a natural language understanding library according to the preset object;
and the second processing submodule is used for scoring each statement in the conversation content according to the target vertical class to obtain a score value corresponding to each statement.
12. The apparatus according to any one of claims 7-11, wherein the apparatus further comprises a determining unit and a transmitting unit;
the determining unit is used for determining a target object matched with the attention degree of the multi-dimensional attribute from a preset object library according to the attention degree of the target user to the multi-dimensional attribute of the preset object;
and the sending unit is used for sending the information of the target object to the client of the target user.
13. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the information processing method of any one of claims 1 to 6.
14. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the information processing method according to any one of claims 1 to 6.
15. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the information processing method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110915000.4A CN113657110A (en) | 2021-08-10 | 2021-08-10 | Information processing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110915000.4A CN113657110A (en) | 2021-08-10 | 2021-08-10 | Information processing method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113657110A true CN113657110A (en) | 2021-11-16 |
Family
ID=78479399
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110915000.4A Pending CN113657110A (en) | 2021-08-10 | 2021-08-10 | Information processing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113657110A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018223534A1 (en) * | 2017-06-09 | 2018-12-13 | 平安科技（深圳）有限公司 | Multi-source data categorization method and server |
| CN111104495A (en) * | 2019-11-19 | 2020-05-05 | 深圳追一科技有限公司 | Information interaction method, device, equipment and storage medium based on intention recognition |
| CN111681647A (en) * | 2020-06-10 | 2020-09-18 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for recognizing word slot |
| CN112069300A (en) * | 2020-09-04 | 2020-12-11 | 中国平安人寿保险股份有限公司 | Semantic recognition method and device for task-based dialog, electronic equipment and storage medium |
| CN112269867A (en) * | 2020-11-17 | 2021-01-26 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for pushing information |
| CN112463971A (en) * | 2020-09-15 | 2021-03-09 | 杭州商情智能有限公司 | E-commerce commodity classification method and system based on hierarchical combination model |
| US10943583B1 (en) * | 2017-07-20 | 2021-03-09 | Amazon Technologies, Inc. | Creation of language models for speech recognition |
| CN112559715A (en) * | 2020-12-24 | 2021-03-26 | 北京百度网讯科技有限公司 | Attitude identification method, attitude identification device, attitude identification equipment and storage medium |
-
2021
- 2021-08-10 CN CN202110915000.4A patent/CN113657110A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018223534A1 (en) * | 2017-06-09 | 2018-12-13 | 平安科技（深圳）有限公司 | Multi-source data categorization method and server |
| US10943583B1 (en) * | 2017-07-20 | 2021-03-09 | Amazon Technologies, Inc. | Creation of language models for speech recognition |
| CN111104495A (en) * | 2019-11-19 | 2020-05-05 | 深圳追一科技有限公司 | Information interaction method, device, equipment and storage medium based on intention recognition |
| CN111681647A (en) * | 2020-06-10 | 2020-09-18 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for recognizing word slot |
| CN112069300A (en) * | 2020-09-04 | 2020-12-11 | 中国平安人寿保险股份有限公司 | Semantic recognition method and device for task-based dialog, electronic equipment and storage medium |
| CN112463971A (en) * | 2020-09-15 | 2021-03-09 | 杭州商情智能有限公司 | E-commerce commodity classification method and system based on hierarchical combination model |
| CN112269867A (en) * | 2020-11-17 | 2021-01-26 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for pushing information |
| CN112559715A (en) * | 2020-12-24 | 2021-03-26 | 北京百度网讯科技有限公司 | Attitude identification method, attitude identification device, attitude identification equipment and storage medium |
Non-Patent Citations (5)
| Title |
|---|
| AHMAD ABDELLATIF等: "A Comparison of Natural Language Understanding Platforms for Chatbots in Software Engineering", IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, pages 1 - 19 * |
| FRANCESCO LOCATELLO等: "Object-Centric Learning with Slot Attention", ARXIV, pages 1 - 27 * |
| 令狐曦: "桔子互动_百度UNIT平台简介", pages 1 - 3, Retrieved from the Internet <URL:知乎 https://zhuanlan.zhihu.com/p/33615420> * |
| 秦美林: "一个汽车问答领域的中文自然语言理解子***的设计与实现", 中国优秀博硕士学位论文全文数据库(硕士), pages 1 - 67 * |
| 黄春梅等: "基于词袋模型和TF-IDF的短文本分类研究", 软件工程, pages 1 - 3 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114548110A (en) | Semantic understanding method and device, electronic equipment and storage medium | |
| US20220291001A1 (en) | Method and apparatus for generating vehicle navigation path | |
| CN112528641A (en) | Method and device for establishing information extraction model, electronic equipment and readable storage medium | |
| CN110675867A (en) | Intelligent dialogue method and device, computer equipment and storage medium | |
| CN113641805A (en) | Acquisition method of structured question-answering model, question-answering method and corresponding device | |
| CN113032258B (en) | Electronic map testing method and device, electronic equipment and storage medium | |
| CN113157877A (en) | Multi-semantic recognition method, device, equipment and medium | |
| CN113641829A (en) | Method and device for training neural network of graph and complementing knowledge graph | |
| CN112784050A (en) | Method, device, equipment and medium for generating theme classification data set | |
| CN117271884A (en) | Method, device, electronic equipment and storage medium for determining recommended content | |
| CN114722171B (en) | Multi-round dialogue processing method and device, electronic equipment and storage medium | |
| CN114490969B (en) | Question and answer method and device based on table and electronic equipment | |
| CN113743127B (en) | Task type dialogue method, device, electronic equipment and storage medium | |
| CN115794742A (en) | File path data processing method, device, equipment and storage medium | |
| CN113657110A (en) | Information processing method and device and electronic equipment | |
| CN116226173A (en) | Data query method, device, storage medium and electronic equipment | |
| CN115455961A (en) | Text processing method, device, equipment and medium | |
| CN114880498A (en) | Event information display method and device, equipment and medium | |
| CN114118937A (en) | Information recommendation method and device based on task, electronic equipment and storage medium | |
| CN113360590A (en) | Method and device for updating point of interest information, electronic equipment and storage medium | |
| CN114141236A (en) | Language model updating method and device, electronic equipment and storage medium | |
| CN113033179A (en) | Knowledge acquisition method and device, electronic equipment and readable storage medium | |
| CN116244413B (en) | New intention determining method, apparatus and storage medium | |
| CN115131709B (en) | Video category prediction method, training method and device for video category prediction model | |
| US20230132618A1 (en) | Method for denoising click data, electronic device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |