CN111160989B - Information processing method and device - Google Patents
Information processing method and device Download PDFInfo
- Publication number
- CN111160989B CN111160989B CN201911424393.8A CN201911424393A CN111160989B CN 111160989 B CN111160989 B CN 111160989B CN 201911424393 A CN201911424393 A CN 201911424393A CN 111160989 B CN111160989 B CN 111160989B
- Authority
- CN
- China
- Prior art keywords
- product
- keyword
- keywords
- target sentence
- processed
- 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.)
- Active
Links
Classifications
-
- 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
- G06Q30/01—Customer relationship services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides an information processing method and device, wherein the method comprises the following steps: under the condition of receiving a preset processing instruction, acquiring information in the preset processing instruction; the information at least comprises: a time period of communication with the customer; calling the audio and video generated by the client in the communication time period to obtain the audio to be processed and the video to be processed; converting the audio to be processed into characters; determining purchase intention information of product keywords in a target sentence; the target sentence is a sentence containing a first intention keyword and a first product keyword in the text; and determining the purchase intention degree of the customer for the product indicated by the product keyword in the target sentence according to the purchase intention information of the product keyword in the target sentence and the line-of-sight stay time of the customer for the product indicated by the product keyword in the target sentence in the video to be processed. The purchase intention degree determined by the method is more objective, so that the accuracy of information input into a specified system is higher.
Description
Technical Field
The present disclosure relates to the field of electronic information, and in particular, to an information processing method and apparatus.
Background
After marketing the product to the customer, the marketing personnel needs to input the communication information with the customer and the judgment result of the purchase intention of the customer for the product into the appointed system.
Currently, marketers determine the results of the decisions of the communication with the customers and the purchase intent of the customers for the products based on the information recorded in the field and recall.
However, the accuracy of the information entered into the designated system is low.
Disclosure of Invention
The application provides an information processing method and device, and aims to solve the problem of low accuracy of information input into a specified system.
In order to achieve the above object, the present application provides the following technical solutions:
the application provides an information processing method, which comprises the following steps:
under the condition that a preset processing instruction is received, acquiring information in the preset processing instruction; the information at least comprises: a time period of communication with the customer;
calling the audio and video generated by the client in the communication time period to obtain audio to be processed and video to be processed;
converting the audio to be processed into characters;
determining purchase intention information of product keywords in a target sentence; the target sentence is a sentence containing a first intention keyword and a first product keyword in the text; the purchase intention information includes: tendering purchases, refusing purchases, and intent to determine;
and determining the purchase intention degree of the client for the product indicated by the product keyword in the target sentence according to the purchase intention information of the product keyword in the target sentence and the stay time of the client's line of sight for the product indicated by the product keyword in the target sentence in the video to be processed.
Optionally, the determining the purchase intention information of the product keywords in the target sentence includes:
identifying the intention keywords in the words according to the preset intention keywords to obtain intention keywords to be processed;
identifying the product keywords in the characters according to preset product keywords to obtain product keywords to be processed;
at least taking the product keywords with the occurrence frequency larger than a preset threshold value in the product keywords to be processed as the product keywords meeting preset conditions;
respectively carrying out sentence expansion on each to-be-processed intention keyword until the to-be-processed intention keywords are expanded to contain any product keyword meeting the preset condition, so as to obtain a target sentence;
and inputting the target sentence into the trained model to obtain the purchase intention information of the product keywords in the target sentence.
Optionally, the determining the purchase intention degree of the client for the product indicated by the product keyword in the target sentence according to the purchase intention information of the product keyword in the target sentence and the line-of-sight stay time of the client for the product indicated by the product keyword in the target sentence in the video to be processed includes:
under the condition that the purchase intention information of the product keywords in the target sentence contains tendency purchases, determining the line-of-sight stay time of the products indicated by the product keywords which are tendency purchases by the clients respectively from the video to be processed;
determining the ratio of the line-of-sight stay time of the product indicated by each product keyword prone to purchase to the total time of the video to be processed respectively, and obtaining the time ratio of the product indicated by each product keyword prone to purchase;
and determining the purchase intention degree of the product indicated by each product keyword which is prone to be purchased by the client according to the purchase intention information of the product keyword which is prone to be purchased and the time ratio of the product indicated by the product keyword which is prone to be purchased.
Optionally, the determining the purchase intention degree of the client for the product indicated by the product keyword in the target sentence according to the purchase intention information of the product keyword in the target sentence and the line-of-sight stay time of the client for the product indicated by the product keyword in the target sentence in the video to be processed includes:
and outputting the information of the product indicated by the product keyword refused to purchase under the condition that the purchase intention information of the product keyword in the target sentence contains the purchase refused.
Optionally, the determining the purchase intention degree of the client for the product indicated by the product keyword in the target sentence according to the purchase intention information of the product keyword in the target sentence and the line-of-sight stay time of the client for the product indicated by the product keyword in the target sentence in the video to be processed includes:
under the condition that the purchase intention information of the product keywords in the target sentence contains intention to be determined, determining the line-of-sight stay time of the products indicated by the product keywords of each intention to be determined by the client from the video to be processed;
determining the ratio of the line-of-sight stay time of the product indicated by the product key word of each intention to be determined to the total time of the video to be processed respectively to obtain the time ratio of the product indicated by the product key word of each intention to be determined;
and determining the purchase intention degree of the product indicated by each product keyword to be determined by the client according to the purchase intention information of the product keyword to be determined and the time ratio of the product indicated by the product keyword to be determined.
Optionally, the video to be processed is a video acquired through a 5G technology.
The application also provides an information processing apparatus, comprising:
the acquisition module is used for acquiring information in the preset processing instruction under the condition that the preset processing instruction is received; the information at least comprises: a time period of communication with the customer;
the calling module is used for calling the audio and the video generated by the client in the communication time period to obtain the audio to be processed and the video to be processed;
the conversion module is used for converting the audio to be processed into characters;
the first determining module is used for determining purchase intention information of the product keywords in the target sentence; the target sentence is a sentence containing a first intention keyword and a first product keyword in the text; the purchase intention information includes: tendering purchases, refusing purchases, and intent to determine;
and the second determining module is used for determining the purchase intention degree of the client for the product indicated by the product keyword in the target sentence according to the purchase intention information of the product keyword in the target sentence and the line-of-sight stay time of the client for the product indicated by the product keyword in the target sentence in the video to be processed.
Optionally, the first determining module is configured to determine purchase intention information of a product keyword in the target sentence, and includes:
the first determining module is specifically configured to identify an intent keyword in the text according to the preset intent keyword, so as to obtain an intent keyword to be processed;
identifying the product keywords in the characters according to preset product keywords to obtain product keywords to be processed;
at least taking the product keywords with the occurrence frequency larger than a preset threshold value in the product keywords to be processed as the product keywords meeting preset conditions;
respectively carrying out sentence expansion on each to-be-processed intention keyword until the to-be-processed intention keywords are expanded to contain any product keyword meeting the preset condition, so as to obtain a target sentence;
and inputting the target sentence into the trained model to obtain the purchase intention information of the product keywords in the target sentence.
Optionally, the second determining module is configured to determine, according to purchase intention information of the product keyword in the target sentence and line-of-sight stay time of the client in the video to be processed for the product indicated by the product keyword in the target sentence, purchase intention degree of the client for the product indicated by the product keyword in the target sentence, where the determining includes:
the second determining module is specifically configured to determine, when purchase intention information of the product keywords in the target sentence includes tendency purchases, line-of-sight stay lengths of products indicated by the product keywords that the client has tendency purchases for each of the products from the video to be processed;
determining the ratio of the line-of-sight stay time of the product indicated by each product keyword prone to purchase to the total time of the video to be processed respectively, and obtaining the time ratio of the product indicated by each product keyword prone to purchase;
and determining the purchase intention degree of the product indicated by each product keyword which is prone to be purchased by the client according to the purchase intention information of the product keyword which is prone to be purchased and the time ratio of the product indicated by the product keyword which is prone to be purchased.
Optionally, the second determining module is configured to determine, according to purchase intention information of the product keyword in the target sentence and line-of-sight stay time of the client in the video to be processed for the product indicated by the product keyword in the target sentence, purchase intention degree of the client for the product indicated by the product keyword in the target sentence, where the determining includes:
the second determining module is specifically configured to output, when purchase rejection information of the product keyword in the target sentence includes purchase rejection information of the product indicated by the product keyword.
Optionally, the second determining module is configured to determine, according to purchase intention information of the product keyword in the target sentence and line-of-sight stay time of the client in the video to be processed for the product indicated by the product keyword in the target sentence, purchase intention degree of the client for the product indicated by the product keyword in the target sentence, where the determining includes:
the second determining module is specifically configured to determine, when purchase intention information of the product keywords in the target sentence includes intention to be determined, line-of-sight stay lengths of products indicated by the product keywords of the intention to be determined by the client respectively from the video to be processed;
determining the ratio of the line-of-sight stay time of the product indicated by the product key word of each intention to be determined to the total time of the video to be processed respectively to obtain the time ratio of the product indicated by the product key word of each intention to be determined;
and determining the purchase intention degree of the product indicated by each product keyword to be determined by the client according to the purchase intention information of the product keyword to be determined and the time ratio of the product indicated by the product keyword to be determined.
Optionally, the video to be processed is a video acquired through a 5G technology.
In the information processing method and device, under the condition that a preset processing instruction is received, information in the preset processing instruction is acquired, and the information at least comprises: a time period of communication with the customer; and retrieving the audio and video generated by the client in the communication time period to obtain the audio to be processed and the video to be processed.
On the one hand, converting the audio to be processed into characters; the purchase intention information of the product keywords in the target sentences is determined, and the target sentences are sentences containing the first intention keywords and the first product keywords, so that the target sentences contain the corresponding relations between the intention keywords and the product keywords, and the intention keywords objectively reflect the purchase intention of the client, so that the purchase intention information of the product keywords can be determined from the target sentences, wherein the purchase intention information comprises the following components: tended to purchase, refused to purchase, and intent to be determined, so that the purchase intent information of any product keyword can objectively reflect the purchase intent degree of the customer for the product indicated by the product keyword;
on the other hand, the stay time of the line of sight of the customer on the product indicated by the product keyword in the target sentence in the video to be processed can objectively reflect the purchase intention degree of the customer on the product indicated by the product keyword in the target sentence;
therefore, according to the purchase intention information of the product keywords in the target sentences and the line-of-sight stay time of the customer in the video to be processed for the products indicated by the product keywords in the target sentences, the purchase intention degree of the customer for the products indicated by the product keywords in the target sentences is determined to be more objective, and accordingly the accuracy of the information input into the appointed system is higher.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an information processing method disclosed in an embodiment of the present application;
fig. 2 is a schematic diagram of an information processing apparatus according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The information processing method provided by the embodiment of the application can be applied to a financial product marketing scene, and of course, can also be applied to other product marketing scenes.
Fig. 1 is a schematic diagram of an information processing method according to an embodiment of the present application, including the following steps:
s101, under the condition that a preset processing instruction is received, acquiring information in the preset processing instruction.
In this step, the preset processing instruction is used to indicate an instruction to start execution in this embodiment, and in practice, the specific form and specific content of the preset processing instruction are not limited in this embodiment.
In this embodiment, the information carried by the preset processing instruction at least includes: a time period, wherein the time period represents a time period during which the marketer communicates with the customer. In this step, the information carried by the preset processing instruction may further include a client identifier, a telephone, etc., where the client identifier is used to uniquely identify the client, specifically, the client identifier may be a client name, and of course, in reality, the client identifier may also be other contents, and in this embodiment, the specific content of the client identifier is not limited. Of course, in practice, other information may also be included in the information carried by the preset post-processing instruction.
S102, according to a time period in a preset processing instruction, calling the time period and the audio data and video data of the client to obtain audio to be processed and video to be processed.
The video data in the step is the video acquired by the 5G technology, and the pictures in the video data are clearer due to the high speed and low time delay of the 5G technology.
In this step, the video and audio of the time period are called according to the time period in the preset processing instruction.
In order to ensure that the called video is a video communicated with the client, in this embodiment, a face image is obtained from the called video, and when the client indicated by the face image and the client indicated by the client identifier are the same client, the called video is taken as a video to be processed, and the called audio is taken as audio to be processed.
S103, converting the audio to be processed into characters.
In this step, the audio to be processed is converted into the text.
Alternatively, the text into which the audio to be processed is converted may also be editable text.
Specifically, the specific implementation manner of converting text in this step is the prior art, and will not be described herein.
S104, identifying the intention keywords in the words according to the preset intention keywords to obtain the intention keywords to be processed.
In this step, the preset intention keywords may be "like", "dislike", "tendency", "unwanted", "consider", etc., and in particular, the specific content of the preset intention keywords needs to be set according to the actual situation, and the embodiment does not limit the specific content of the preset intention keywords.
In this step, the intent keywords appearing in the text are identified according to the preset intent keywords, and for convenience of description, the intent keywords identified from the text are referred to as intent keywords to be processed.
S105, identifying the product keywords from the characters according to the preset product keywords, and obtaining the product keywords to be processed.
In this step, the preset product keywords may include: the product name, the product type, the risk type, etc., in practice, the preset product keyword may further include other contents, and the embodiment does not limit the specific contents of the preset product keyword, so long as the preset product keyword may indicate a financial product.
In this step, the specific implementation manner of identifying the product keywords from the text is the prior art, and will not be described here again. For convenience of description, the product keywords identified in this step are referred to as to-be-processed product keywords.
S106, at least taking the product keywords with the occurrence frequency larger than a preset threshold value in the product keywords to be processed as the product keywords meeting preset conditions.
In the step, the occurrence times of the keywords of the product to be processed are counted, and the keywords of the product with the occurrence times larger than a preset threshold value are used as the keywords of the product meeting the preset condition.
In this embodiment, the product keyword to be processed may also be used as a product keyword that satisfies a preset condition. The present embodiment is not limited to the specific contents of the preset conditions.
S107, respectively carrying out sentence expansion on each to-be-processed intention keyword until the to-be-processed intention keywords are expanded to contain any product keyword meeting the preset condition, and obtaining a target sentence.
For example, the intent keyword to be processed is "tendency", in the text, sentence expansion is performed on "tendency", that is, a sentence composed of the term "tendency" is searched for from the text, for example, a sentence expanded by the term "tendency" is "i prefer a product", and in the case that a product is a product keyword, "i prefer a product" is a target sentence.
For example, the intent keyword to be processed is "dislike", and in the text, sentence expansion is performed on the "dislike", that is, a sentence composed of the word "dislike" is searched for from the text, for example, the obtained sentence is "i dislike high risk", and in the case that the high risk is a product keyword, the sentence is a target sentence.
For another example, the intent keyword to be processed is "consider once", sentence expansion is performed on "consider once" in the text, a sentence formed by the word "consider once" is searched for in the text as "about your opinion, i consider once", since the sentence does not include any product keyword meeting the preset condition, sentence expansion is continued on the basis of the sentence until any product keyword meeting the preset condition is located, and the obtained sentence is used as a target sentence.
In practice, some sentences may exist in the target sentences obtained by the step, and the product keywords in the sentences are the same, but the intention keywords are different, which indicates that the purchase intention of the product indicated by the product keywords is continuously changed. In order to improve the accuracy of the target sentences determined in the step, in this case, the final sentence in the text of the sentences is used as the target sentence according to the sequence of the sentences in the text.
S108, inputting the target sentence into the trained model to obtain the purchase intention information of the product keywords in the target sentence.
In this embodiment, the purchase intention information may include: tend to purchase, refuse to purchase, and intent to be determined.
In this embodiment, the model may be a neural network model, and the model is trained by using a preset sample, where the preset training sample may be: the sentence containing the intention keyword and the product keyword, and the sample label may be purchase intention information of the product keyword of each sentence in the sample. For example, if one statement in the sample is "I prefer A product", then the sample tag for the product key in that sample may be a purchase-prone. Specifically, the training process of the model by using the sample and the sample label is the prior art, and is not described herein.
In the step, after the target sentence is input into the trained model, purchasing trend information corresponding to each product keyword in the target sentence is output.
The purposes of the above S104-S108 are: purchase intention information of the product keywords in the target sentence is determined. The target sentence is a sentence containing a first intention keyword and a first product keyword in the text; the first intention key is any one of preset intention keys; the first product keywords are any one of the product keywords meeting preset conditions.
S109, judging whether the purchase intention information of the product keywords in the target sentence comprises tendency purchase, if so, executing S110, and if not, executing S114.
The specific implementation manner of the judgment in this step is the prior art, and will not be described here again.
S110, determining product keywords prone to purchase.
In the step, corresponding product keywords tend to be purchased are determined from the product keywords of the target sentence, and the product keywords tend to be purchased are obtained.
For example, in this step, the product keywords that are intended to be purchased are "A product", "B product", and "C product", respectively.
S111, determining the line-of-sight stay time of the customer for the product indicated by the product keyword which tends to be purchased from the video to be processed.
Also taking the product keywords which tend to be purchased as "A product", "B product" and "C product" respectively as an example, in this step, the line-of-sight stay time of the customer for the products indicated by "A product", "B product" and "C product" respectively is determined from the video to be processed. And obtaining the line-of-sight stay time of the product indicated by the product A, the line-of-sight stay time of the product indicated by the product B and the line-of-sight stay time of the product indicated by the product C.
The specific implementation manner is the prior art and will not be described herein.
S112, determining the ratio of the line-of-sight stay time of the product indicated by the product key word of each tendency to purchase to the total time of the video to be processed, and obtaining the time ratio of the product indicated by the product key word of each tendency to purchase.
The specific implementation manner of this step is the prior art, and will not be described here again.
S113, determining the purchase intention degree of the product indicated by each product keyword which is prone to be purchased according to the purchase intention information of the product keyword which is prone to be purchased and the time ratio of the product indicated by the product keyword which is prone to be purchased.
In this step, the greater the time ratio of the product indicated by any one of the purchase-prone product keywords, the greater the purchase intention of the customer for the product indicated by that purchase-prone product keyword.
Alternatively, in this embodiment, different weights may be set for different purchase intentions of the product keywords in the target sentence, which is referred to as a first weight, where the higher the purchase intention is, the greater the first weight value of the product keywords. And, a weight may be set for the duration ratio of the product keyword in the target sentence, which is called a second weight, where the greater the duration ratio is, the greater the second weight value of the product keyword of the product.
In this embodiment, for any product keyword in the target sentence, a final weight value of the product keyword may be obtained by calculation according to a preset calculation rule according to the first weight and the second weight of the product keyword, where the final weight value represents the attention degree of the customer to the product indicated by the product keyword.
S114, judging whether purchase rejection is contained in purchase intention information of the product keywords in the target sentence, if so, executing S115, and if not, executing S116.
S115, outputting information of the products indicated by the product keywords refused to purchase.
In the case where purchase rejection is included in the purchase intention information of the product keyword in the target sentence, this step is performed, and since the purchase intention is already purchase rejection, it is not necessary to determine the line-of-sight stay time of the customer for the product indicated by the purchase rejection product keyword. Therefore, in this step, the information of the product indicated by the product keyword refused to purchase is directly output.
S116, judging whether purchase intention information of the product keywords in the target sentence contains intention to be determined, if so, executing S117, and if not, ending.
S117, determining the line-of-sight stay time of the products indicated by the product keywords of each intention to be determined from the videos to be processed.
Specifically, the specific implementation manner of this step is the prior art, and will not be described herein.
S118, determining the ratio of the line-of-sight stay time of the product indicated by the product key word of each intention to be determined to the total time of the video to be processed, and obtaining the time ratio of the product indicated by the product key word of each intention to be determined.
S119, determining the purchase intention degree of the products indicated by the product keywords to be determined according to the purchase intention information of the product keywords to be determined and the time ratio of the products indicated by the product keywords to be determined.
In this step, the greater the time ratio of the product indicated by any of the intended product keywords, the higher the purchase intention of the customer for the product indicated by the intended product keywords.
The purpose of the above S109-S119 is: and determining the purchase intention degree of the client for the product indicated by the product keyword in the target sentence according to the purchase intention information of the product keyword in the target sentence and the line-of-sight stay time of the client for the product indicated by the product keyword in the target sentence in the video to be processed.
The beneficial effects of the embodiment of the application include:
the beneficial effects are as follows:
in the application, on one hand, audio to be processed is converted into characters; the purchase intention information of the product keywords in the target sentences is determined, and the target sentences are sentences containing the first intention keywords and the first product keywords, so that the target sentences contain the corresponding relations between the intention keywords and the product keywords, and the intention keywords objectively reflect the purchase intention of the client, so that the purchase intention information of the product keywords can be determined from the target sentences, wherein the purchase intention information comprises the following components: tended to purchase, refused to purchase, and intent to be determined, so that the purchase intent information of any product keyword can objectively reflect the purchase intent degree of the customer for the product indicated by the product keyword;
on the other hand, the stay time of the line of sight of the customer on the product indicated by the product keyword in the target sentence in the video to be processed can objectively reflect the purchase intention degree of the customer on the product indicated by the product keyword in the target sentence;
therefore, according to the purchase intention information of the product keywords in the target sentences and the line-of-sight stay time of the customer in the video to be processed for the products indicated by the product keywords in the target sentences, the purchase intention degree of the customer for the products indicated by the product keywords in the target sentences is determined to be more objective, and accordingly the accuracy of the information input into the appointed system is higher.
The beneficial effects are as follows:
in this embodiment, since the video to be processed is acquired through the 5G technology, due to the low time delay and high speed of the 5G technology, the image of the video to be processed is clearer, and further, the accuracy of determining the line-of-sight stay time of the product indicated by the product keyword in the target sentence in the video to be processed is higher, and further, the finally determined purchase intention degree of the customer on the product indicated by the product keyword in the target sentence is more accurate.
Fig. 2 is a schematic diagram of an information processing apparatus according to an embodiment of the present application, including: the device comprises an acquisition module 201, a calling module 202, a conversion module 203, a first determination module 204 and a second determination module 205.
An obtaining module 201, configured to obtain information in a preset processing instruction when receiving the preset processing instruction; the information at least comprises: time period of communication with the customer.
And the calling module 202 is used for calling the audio and the video generated by the client in the communication time period to obtain the audio to be processed and the video to be processed.
The conversion module 203 is configured to convert the audio to be processed into text.
A first determining module 204, configured to determine purchase intention information of the product keywords in the target sentence; the target sentence is a sentence containing a first intention keyword and a first product keyword in the text; the purchase intention information includes: tend to purchase, refuse to purchase, and intent to be determined.
The second determining module 205 is configured to determine, according to purchase intention information of the product keywords in the target sentence and a line of sight stay time of the client in the video to be processed for the product indicated by the product keywords in the target sentence, a purchase intention degree of the client for the product indicated by the product keywords in the target sentence.
Optionally, the first determining module 204 is configured to determine purchase intention information of the product keyword in the target sentence, including:
the first determining module 204 is specifically configured to identify intent keywords in the text according to preset intent keywords, so as to obtain intent keywords to be processed; identifying product keywords in the characters according to preset product keywords to obtain product keywords to be processed; at least taking the product keywords with the occurrence frequency larger than a preset threshold value in the product keywords to be processed as the product keywords meeting preset conditions; respectively carrying out sentence expansion on each to-be-processed intention keyword until the to-be-processed intention keywords are expanded to contain any product keyword meeting preset conditions, so as to obtain a target sentence; and inputting the target sentence into the trained model to obtain the purchase intention information of the product keyword in the target sentence.
Optionally, the second determining module 205 is configured to determine, according to purchase intention information of the product keyword in the target sentence and a line-of-sight stay time of the product indicated by the product keyword in the target sentence by the client in the video to be processed, a purchase intention degree of the product indicated by the product keyword in the target sentence by the client, where the determining includes:
the second determining module 205 is specifically configured to determine, when the purchase intention information of the product keyword in the target sentence includes a tendency to purchase, a line of sight stay period of the product indicated by the product keyword that the customer purchases for each tendency, from the video to be processed; determining the ratio of the line-of-sight stay time of the product indicated by the product key word of each tendency to purchase to the total time of the video to be processed respectively to obtain the time ratio of the product indicated by the product key word of each tendency to purchase; and determining the purchase intention degree of the product indicated by each product keyword which is prone to be purchased by the customer according to the purchase intention information of the product keyword which is prone to be purchased and the time ratio of the product indicated by the product keyword which is prone to be purchased.
Optionally, the second determining module 205 is configured to determine, according to purchase intention information of a product keyword in a target sentence and a line of sight stay time of a client in a video to be processed for a product indicated by the product keyword in the target sentence, a purchase intention degree of the client for the product indicated by the product keyword in the target sentence, where the determining includes:
the second determining module 205 is specifically configured to output, when purchase rejection information of the product keyword in the target sentence includes purchase rejection information of the product indicated by the product keyword.
Optionally, the second determining module 205 is configured to determine, according to purchase intention information of a product keyword in a target sentence and a line of sight stay time of a client in a video to be processed for a product indicated by the product keyword in the target sentence, a purchase intention degree of the client for the product indicated by the product keyword in the target sentence, where the determining includes:
the second determining module 205 is specifically configured to determine, when the purchase intention information of the product keywords in the target sentence includes the intention to be determined, a line-of-sight stay time of the product indicated by the product keywords of each intention to be determined for the client from the video to be processed;
the ratio of the line-of-sight stay time of the product indicated by each product key word to be determined to the total time of the video to be processed is respectively determined, and the time duty ratio of the product indicated by each product key word to be determined is obtained;
and determining the purchase intention degree of the products indicated by the product keywords of each intention to be determined according to the purchase intention information of the product keywords of the intention to be determined and the time ratio of the products indicated by the product keywords of the intention to be determined.
Optionally, the video to be processed is a video acquired by a 5G technique.
The functions described in the methods of the present application, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computing device readable storage medium. Based on such understanding, a portion of the embodiments of the present application that contributes to the prior art or a portion of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computing device (which may be a personal computer, a server, a mobile computing device or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. An information processing method, characterized by comprising:
under the condition that a preset processing instruction is received, acquiring information in the preset processing instruction; the information at least comprises: a time period of communication with the customer;
calling the audio and video generated by the client in the communication time period to obtain audio to be processed and video to be processed;
converting the audio to be processed into characters;
determining purchase intention information of product keywords in a target sentence; the target sentence is a sentence containing a first intention keyword and a first product keyword in the text; the purchase intention information includes: tendering purchases, refusing purchases, and intent to determine;
determining the purchase intention degree of the client for the product indicated by the product keyword in the target sentence according to the purchase intention information of the product keyword in the target sentence and the stay time of the client's line of sight for the product indicated by the product keyword in the target sentence in the video to be processed;
the determining the purchase intention information of the product keywords in the target sentence comprises the following steps:
identifying the intention keywords in the words according to the preset intention keywords to obtain intention keywords to be processed;
identifying the product keywords in the characters according to preset product keywords to obtain product keywords to be processed;
at least taking the product keywords with the occurrence frequency larger than a preset threshold value in the product keywords to be processed as product keywords meeting preset conditions;
respectively carrying out sentence expansion on each to-be-processed intention keyword until the to-be-processed intention keywords are expanded to contain any product keyword meeting the preset condition, so as to obtain a target sentence; if the product keywords obtained based on different intention keywords are the same, sequencing all sentences containing the product keywords according to the sequence in the characters, and taking the sentence with the last sequence as a target sentence; and inputting the target sentence into the trained model to obtain the purchase intention information of the product keywords in the target sentence.
2. The method according to claim 1, wherein determining the purchase intention degree of the client for the product indicated by the product keyword in the target sentence according to the purchase intention information of the product keyword in the target sentence and the line-of-sight stay time of the client for the product indicated by the product keyword in the target sentence in the video to be processed comprises:
under the condition that the purchase intention information of the product keywords in the target sentence contains tendency purchases, determining the line-of-sight stay time of the products indicated by the product keywords which are tendency purchases by the clients respectively from the video to be processed;
determining the ratio of the line-of-sight stay time of the product indicated by each product keyword prone to purchase to the total time of the video to be processed respectively, and obtaining the time ratio of the product indicated by each product keyword prone to purchase;
and determining the purchase intention degree of the product indicated by each product keyword which is prone to be purchased by the client according to the purchase intention information of the product keyword which is prone to be purchased and the time ratio of the product indicated by the product keyword which is prone to be purchased.
3. The method according to claim 1, wherein determining the purchase intention degree of the client for the product indicated by the product keyword in the target sentence according to the purchase intention information of the product keyword in the target sentence and the line-of-sight stay time of the client for the product indicated by the product keyword in the target sentence in the video to be processed comprises:
and outputting the information of the product indicated by the product keyword refused to purchase under the condition that the purchase intention information of the product keyword in the target sentence contains the purchase refused.
4. The method according to claim 1, wherein determining the purchase intention degree of the client for the product indicated by the product keyword in the target sentence according to the purchase intention information of the product keyword in the target sentence and the line-of-sight stay time of the client for the product indicated by the product keyword in the target sentence in the video to be processed comprises:
under the condition that the purchase intention information of the product keywords in the target sentence contains intention to be determined, determining the line-of-sight stay time of the products indicated by the product keywords of each intention to be determined by the client from the video to be processed;
determining the ratio of the line-of-sight stay time of the product indicated by the product key word of each intention to be determined to the total time of the video to be processed respectively to obtain the time ratio of the product indicated by the product key word of each intention to be determined;
and determining the purchase intention degree of the product indicated by each product keyword to be determined by the client according to the purchase intention information of the product keyword to be determined and the time ratio of the product indicated by the product keyword to be determined.
5. The method of claim 1, wherein the video to be processed is video captured by a 5G technique.
6. An information processing apparatus, characterized by comprising:
the acquisition module is used for acquiring information in the preset processing instruction under the condition that the preset processing instruction is received; the information at least comprises: a time period of communication with the customer;
the calling module is used for calling the audio and the video generated by the client in the communication time period to obtain the audio to be processed and the video to be processed;
the conversion module is used for converting the audio to be processed into characters;
the first determining module is used for determining purchase intention information of the product keywords in the target sentence; the target sentence is a sentence containing a first intention keyword and a first product keyword in the text; the purchase intention information includes: tendering purchases, refusing purchases, and intent to determine;
the second determining module is used for determining the purchase intention degree of the client for the product indicated by the product keyword in the target sentence according to the purchase intention information of the product keyword in the target sentence and the line-of-sight stay time of the client for the product indicated by the product keyword in the target sentence in the video to be processed;
the first determining module is configured to determine purchase intention information of a product keyword in a target sentence, and includes:
the first determining module is specifically configured to identify an intent keyword in the text according to the preset intent keyword, so as to obtain an intent keyword to be processed;
identifying the product keywords in the characters according to preset product keywords to obtain product keywords to be processed;
at least taking the product keywords with the occurrence frequency larger than a preset threshold value in the product keywords to be processed as product keywords meeting preset conditions;
respectively carrying out sentence expansion on each to-be-processed intention keyword until the to-be-processed intention keywords are expanded to contain any product keyword meeting the preset condition, so as to obtain a target sentence; if the product keywords obtained based on different intention keywords are the same, sequencing all sentences containing the product keywords according to the sequence in the characters, and taking the sentence with the last sequence as a target sentence;
and inputting the target sentence into the trained model to obtain the purchase intention information of the product keywords in the target sentence.
7. The apparatus of claim 6, wherein the second determining module, configured to determine, according to purchase intention information of the product keyword in the target sentence and a line-of-sight stay time of the client in the video to be processed for the product indicated by the product keyword in the target sentence, the purchase intention degree of the client for the product indicated by the product keyword in the target sentence, includes:
the second determining module is specifically configured to determine, when purchase intention information of the product keywords in the target sentence includes tendency purchases, line-of-sight stay lengths of products indicated by the product keywords that the client has tendency purchases for each of the products from the video to be processed;
determining the ratio of the line-of-sight stay time of the product indicated by each product keyword prone to purchase to the total time of the video to be processed respectively, and obtaining the time ratio of the product indicated by each product keyword prone to purchase;
and determining the purchase intention degree of the product indicated by each product keyword which is prone to be purchased by the client according to the purchase intention information of the product keyword which is prone to be purchased and the time ratio of the product indicated by the product keyword which is prone to be purchased.
8. The apparatus of claim 6, wherein the second determining module, configured to determine, according to purchase intention information of the product keyword in the target sentence and a line-of-sight stay time of the client in the video to be processed for the product indicated by the product keyword in the target sentence, the purchase intention degree of the client for the product indicated by the product keyword in the target sentence, includes:
the second determining module is specifically configured to output, when purchase rejection information of the product keyword in the target sentence includes purchase rejection information of the product indicated by the product keyword.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911424393.8A CN111160989B (en) | 2019-12-31 | 2019-12-31 | Information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911424393.8A CN111160989B (en) | 2019-12-31 | 2019-12-31 | Information processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111160989A CN111160989A (en) | 2020-05-15 |
| CN111160989B true CN111160989B (en) | 2023-08-08 |
Family
ID=70560715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911424393.8A Active CN111160989B (en) | 2019-12-31 | 2019-12-31 | Information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111160989B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960895A (en) * | 2018-06-07 | 2018-12-07 | 佛山市业鹏机械有限公司 | A kind of sale result analysis system based on pet showing stand |
| CN109727092A (en) * | 2018-12-15 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium based on AI |
| CN110136723A (en) * | 2019-04-15 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Data processing method and device based on voice messaging |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140085613A (en) * | 2012-12-20 | 2014-07-08 | 현대자동차주식회사 | System, server and method for social marketing |
-
2019
- 2019-12-31 CN CN201911424393.8A patent/CN111160989B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108960895A (en) * | 2018-06-07 | 2018-12-07 | 佛山市业鹏机械有限公司 | A kind of sale result analysis system based on pet showing stand |
| CN109727092A (en) * | 2018-12-15 | 2019-05-07 | 深圳壹账通智能科技有限公司 | Products Show method, apparatus, computer equipment and storage medium based on AI |
| CN110136723A (en) * | 2019-04-15 | 2019-08-16 | 深圳壹账通智能科技有限公司 | Data processing method and device based on voice messaging |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111160989A (en) | 2020-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10726446B2 (en) | Method and apparatus for pushing information | |
| US20180336193A1 (en) | Artificial Intelligence Based Method and Apparatus for Generating Article | |
| CN104951428B (en) | User's intension recognizing method and device | |
| CN107633380A (en) | The task measures and procedures for the examination and approval and system of a kind of anti-data-leakage system | |
| CN113392236A (en) | Data classification method, computer equipment and readable storage medium | |
| CN111488813B (en) | Video emotion marking method and device, electronic equipment and storage medium | |
| CN109684444A (en) | A kind of intelligent customer service method and system | |
| CN113705792A (en) | Personalized recommendation method, device, equipment and medium based on deep learning model | |
| CN111787042B (en) | Method and device for pushing information | |
| CN109615458A (en) | Client management method, device, terminal device and computer readable storage medium | |
| CN111160989B (en) | Information processing method and device | |
| CN112800209A (en) | Conversation corpus recommendation method and device, storage medium and electronic equipment | |
| US20150180818A1 (en) | Interface for Product Reviews Identified in Online Reviewer Generated Content | |
| CN108694171B (en) | Information pushing method and device | |
| CN113010664B (en) | Data processing method and device and computer equipment | |
| CN110825954A (en) | Keyword recommendation method and device and electronic equipment | |
| CN114399352A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN110717109B (en) | Method, device, electronic equipment and storage medium for recommending data | |
| CN111368070B (en) | Method and device for determining hot event | |
| KR102078541B1 (en) | Issue interest based news value evaluation apparatus and method, storage media storing the same | |
| CN112328937A (en) | Information delivery method and device | |
| CN110413637B (en) | Information recommendation method, device and equipment | |
| CN112966173B (en) | Classification operation method and device for information comments | |
| CN117573844B (en) | Data recommendation method and device based on context awareness and related medium | |
| CN118094012A (en) | Information recommendation method and device based on privacy protection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |