CN110796495A - Method, device, computer storage medium and terminal for realizing information processing - Google Patents
Method, device, computer storage medium and terminal for realizing information processing Download PDFInfo
- Publication number
- CN110796495A CN110796495A CN201911052314.5A CN201911052314A CN110796495A CN 110796495 A CN110796495 A CN 110796495A CN 201911052314 A CN201911052314 A CN 201911052314A CN 110796495 A CN110796495 A CN 110796495A
- Authority
- CN
- China
- Prior art keywords
- conversation
- sales
- state
- customer
- 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
Images
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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A method, a device, a computer storage medium and a terminal for realizing information processing comprise: analyzing the sales conversation of a preset number of commodities to obtain conversation information containing two or more preset conversation states; constructing a Markov decision process based on the dialogue information which is obtained by analysis and contains each dialogue state; providing real-time dialogue prompt information for a selling user through a constructed Markov decision process; wherein the sales conversation comprises: a conversation between the sales user and the customer. The embodiment of the invention provides conversation prompt information for the real-time sale of the selling user and provides information support for improving the sale level of the selling user through the Markov decision process constructed based on the sale conversation.
Description
Technical Field
The present disclosure relates to, but not limited to, information processing technology, and more particularly, to a method, an apparatus, a computer storage medium, and a terminal for implementing information processing.
Background
With the development of economy, the appeal of people to consumption is gradually enhanced, and the retail industry is developed vigorously. In the physical retail industry, sales are necessary links of the retail industry, and the sales users have the following problems: lack of mature sales skills, low sales levels; the mobility is big, can't carry out the promotion of sales level through the effectual training of system.
In order to improve the sales level of the sales user, the sales user is mainly informed to the sales user in a classroom or network training mode by means of media such as audio, video, books and the like after the sales rule is summarized according to expert sales experience.
The method is based on the sales rule summarized by expert experience, and the effectiveness is difficult to measure; the pertinence of the sales rule needs to be improved, and the method cannot be applied to all complex and variable scenes; in addition, both classroom and network configurations result in long hours of learning and high costs. In summary, how to effectively improve the sales level of the sales user becomes a problem to be solved.
Disclosure of Invention
The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.
The embodiment of the invention provides a method and a device for realizing information processing, a computer storage medium and a terminal, which can improve the sales level of a sales user.
The embodiment of the invention provides a method for realizing information processing, which comprises the following steps:
analyzing the sales conversation of a preset number of commodities to obtain conversation information containing two or more preset conversation states;
constructing a Markov decision process based on the dialogue information which is obtained by analysis and contains each dialogue state;
providing real-time dialogue prompt information for a selling user through a constructed Markov decision process;
wherein the sales conversation comprises: a conversation between the sales user and the customer.
In one exemplary embodiment, the dialog state includes:
the status of the customer in one or any combination of the following: the method comprises the following steps of providing demand, providing a question, providing an auction product, consulting price, consulting preferential, consulting after-sale, determining transaction and rejecting transaction;
the status of the sales user of one or any combination of: welcome, demand communication, recommendation, question answering, brand introduction, preferential content, guest situation and contact information acquisition.
In one exemplary embodiment, the expression of the markov decision process is < S, a, P, R, γ >;
wherein, the expression < S, A, P, R, Gamma > is as follows: s is a conversation information set of each conversation state of a customer, A is a conversation information set of each conversation state of a sales user, P is a state transition matrix in which the conversation states of the customer are transitioned, R is a preset reward value of the conversation state, and gamma is a preset reward attenuation coefficient corresponding to the reward value; the state transition matrix includes: each conversation state of the sales user causes a transition state in which the conversation state of the customer transitions, and transition probabilities corresponding to the respective transition states.
In an exemplary embodiment, the providing the real-time dialog prompt information for the selling user includes:
and the sales user feeds back the conversation state of the next conversation with the customer to the sales user in real time according to the Markov decision process.
On the other hand, an embodiment of the present invention further provides an apparatus for implementing information processing, including: the device comprises an analysis unit, a construction unit and a prompt unit; wherein the content of the first and second substances,
the analysis unit is used for: analyzing the sales conversation of a preset number of commodities to obtain conversation information containing two or more preset conversation states;
the building unit is used for: constructing a Markov decision process based on the dialogue information which is obtained by analysis and contains each dialogue state;
the prompting unit is used for: providing real-time dialogue prompt information for a selling user through a constructed Markov decision process;
wherein the sales conversation comprises: a conversation between the sales user and the customer.
In one exemplary embodiment, the dialog state includes:
the status of the customer in one or any combination of the following: the method comprises the following steps of providing demand, providing a question, providing an auction product, consulting price, consulting preferential, consulting after-sale, determining transaction and rejecting transaction;
the status of the sales user of one or any combination of: welcome, demand communication, recommendation, question answering, brand introduction, preferential content, guest situation and contact information acquisition.
In one exemplary embodiment, the expression of the markov decision process is < S, a, P, R, γ >;
wherein, the expression < S, A, P, R, Gamma > is as follows: s is a conversation information set of each conversation state of a customer, A is a conversation information set of each conversation state of a sales user, P is a state transition matrix in which the conversation states of the customer are transitioned, R is a preset reward value of the conversation state, and gamma is a preset reward attenuation coefficient corresponding to the reward value; the state transition matrix includes: each conversation state of the sales user causes a transition state in which the conversation state of the customer transitions, and transition probabilities corresponding to the respective transition states.
In an exemplary embodiment, the prompting unit is specifically configured to:
and according to the Markov decision process, feeding back the conversation state of the next conversation with the customer to the sales user in real time.
In still another aspect, an embodiment of the present invention further provides a computer storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method for implementing information processing is implemented.
In another aspect, an embodiment of the present invention further provides a terminal, including: a memory and a processor, the memory having a computer program stored therein; wherein the content of the first and second substances,
the processor is configured to execute the computer program in the memory;
the computer program, when executed by the processor, implements a method of implementing information processing as described above.
Compared with the related art, the technical scheme of the application comprises the following steps: analyzing the sales conversation of a preset number of commodities to obtain conversation information containing two or more preset conversation states; constructing a Markov decision process based on the dialogue information which is obtained by analysis and contains each dialogue state; providing real-time dialogue prompt information for a selling user through a constructed Markov decision process; wherein the sales conversation comprises: a conversation between the sales user and the customer. The embodiment of the invention provides conversation prompt information for the real-time sale of the selling user and provides information support for improving the sale level of the selling user through the Markov decision process constructed based on the sale conversation.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the example serve to explain the principles of the invention and not to limit the invention.
FIG. 1 is a flow chart of a method for implementing information processing according to an embodiment of the present invention;
fig. 2 is a block diagram of an apparatus for implementing information processing according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
The steps illustrated in the flow charts of the figures may be performed in a computer system such as a set of computer-executable instructions. Also, while a logical order is shown in the flow diagrams, in some cases, the steps shown or described may be performed in an order different than here.
Fig. 1 is a flowchart of a method for implementing information processing according to an embodiment of the present invention, as shown in fig. 1, including:
wherein the sales conversation comprises: a conversation between the sales user and the customer.
It should be noted that the number of sales sessions in the embodiment of the present invention may be set by a person skilled in the art according to experience, for example, setting a sales session for sales of 200 or more groups of commodities;
in one exemplary embodiment, the sales dialog used to construct the Markov decision process may contain sales dialogs for a plurality of categories of goods; the proportion of sales sessions for various types of goods may be set by experience of those skilled in the art; for example, the ratio may be set according to the categories of commodities sold by the sales users to which the embodiment of the present invention is applied; if the sales user who applies the embodiment of the invention is a user selling clothes, a sales conversation for selling clothes with a larger proportion can be adopted; the specific proportion can be set by the technicians in the field according to experience, and can be adjusted according to the sales effect after the sales prompt information is provided.
In one exemplary embodiment, the sales dialog used to construct the Markov decision process may contain only sales dialogs for one commodity; the category of the sales conversation may be a category of goods sold by the sales user to which the embodiment of the present invention is applied; for example, if the sales user is a user selling clothing, the sales dialog for constructing the markov decision process is the sales dialog for selling clothing;
in an exemplary embodiment, the sales dialog may include sales dialogs of sales users of a plurality of different sales levels, the sales dialogs including both sales successful dialogs and sales failed dialogs.
In an exemplary embodiment, to construct a markov decision process, the dialog messages of an embodiment of the present invention are formatted in text. The format in which the sales dialog may be formatted may include: video, audio, or text; to construct the markov decision process, the sales dialog, which is not in the text format, needs to be converted into the text format, and text-formatted dialog information used for constructing the markov decision process is generated based on the conversion, for example, before obtaining the dialog information, information included in the sales dialog may be recognized by using an Automatic Speech Recognition (ASR) technique, a text-formatted file is generated, and after the text-formatted file is parsed and generated, dialog information of a preset dialog state is obtained.
In an exemplary embodiment, the dialog states include, but are not limited to:
the status of the customer in one or any combination of the following: the method comprises the following steps of providing demand, providing a question, providing an auction product, consulting price, consulting preferential, consulting after-sale, determining transaction, rejecting transaction and the like;
the status of the sales user of one or any combination of: welcome, demand communication, recommendation, question answering, brand introduction, preferential content, guest situation, contact information acquisition and the like.
It should be noted that the dialog state in the embodiment of the present invention may be obtained by parsing a set model or rule based on a text analysis method in the related art. The embodiment of the invention can also set other conversation states according to the sales process.
102, constructing a Markov decision process based on the dialogue information which is obtained by analysis and contains each dialogue state;
in one exemplary embodiment, the expression of the markov decision process is < S, a, P, R, γ >;
wherein, the expression < S, A, P, R, Gamma > is as follows: s is a conversation information set of each conversation state of a customer, A is a conversation information set of each conversation state of a sales user, P is a state transition matrix in which the conversation states of the customer are transitioned, R is a preset reward value of the conversation state, and gamma is a preset reward attenuation coefficient corresponding to the reward value; the state transition matrix includes: each conversation state of the sales user causes a transition state in which the conversation state of the customer transitions, and transition probabilities corresponding to the respective transition states.
In an exemplary embodiment, the reward value for the dialog state may be set according to the following rules:
the reward value for the session state that completes the transaction is 1, the reward value for the session state that rejects the transaction is-1, and the reward values for the other session states are 0.
In an exemplary embodiment, the value range of the reward attenuation coefficient is 0-1, and can be set by experience values of those skilled in the art, and the closer the reward attenuation coefficient is to 1, the more deliberate return can be represented.
Table 1 is an example table of a state transition matrix according to an embodiment of the present invention, where a session state of a customer in table 1 includes: demand raising, question raising, contest raising, price consulting, transaction determining, transaction refusing and the like; the dialog states of the sales user include: welcome, demand communication, recommendation, question answering, guest's feelings, contact information acquisition and the like; the transition probability of the customer dialog state transition caused by each dialog state of the sales user can be recorded through table 1:
TABLE 1
103, providing real-time dialogue prompt information for the sales user through the constructed Markov decision process;
in an exemplary embodiment, the providing the real-time dialog prompt information for the selling user includes:
and according to the Markov decision process, feeding back the conversation state of the next conversation with the customer to the sales user in real time.
It should be noted that the dialog state of the subsequent dialog here includes: in the real-time sale process, after a customer expresses the content of a conversation state to a sale user according to a purchase requirement, the sale user responds to the conversation state of a conversation of a reply; for example, after a customer expresses his/her needs to a sales user according to a purchase request, that is, expresses content of a demand, according to a markov decision process, the embodiment of the present invention feeds back to the sales user in real time an appropriate dialog state of a dialog that should be performed for the demand state of the customer, such as, recommending: the recommendation process comprises the following steps: introducing related products;
in an exemplary embodiment, the method of an embodiment of the present invention further includes:
and updating the constructed Markov decision process according to the newly added sales dialogue.
The embodiment of the invention can provide more accurate sales prompt information for the sales user through the iterative update of the newly added sales dialogue.
Compared with the related art, the technical scheme of the application comprises the following steps: analyzing the sales conversation of a preset number of commodities to obtain conversation information containing two or more preset conversation states; constructing a Markov decision process based on the dialogue information which is obtained by analysis and contains each dialogue state; providing real-time dialogue prompt information for a selling user through a constructed Markov decision process; wherein the sales conversation comprises: a conversation between the sales user and the customer. The embodiment of the invention provides conversation prompt information for the real-time sale of the selling user and provides information support for improving the sale level of the selling user through the Markov decision process constructed based on the sale conversation.
Fig. 2 is a block diagram of an apparatus for implementing information processing according to an embodiment of the present invention, as shown in fig. 2, including: the device comprises an analysis unit, a construction unit and a prompt unit; wherein the content of the first and second substances,
the analysis unit is used for: analyzing the sales conversation of a preset number of commodities to obtain conversation information containing two or more preset conversation states;
wherein the sales conversation comprises: a conversation between the sales user and the customer.
In an exemplary embodiment, to construct a markov decision process, the dialog messages of an embodiment of the present invention are formatted in text.
It should be noted that the number of sales sessions in the embodiment of the present invention may be set by a person skilled in the art according to experience, for example, setting a sales session for sales of 200 or more groups of commodities;
in one exemplary embodiment, the sales dialog used to construct the Markov decision process may contain sales dialogs for a plurality of categories of goods; the proportion of sales sessions for various types of goods may be set by experience of those skilled in the art; for example, the ratio may be set according to the categories of commodities sold by the sales users to which the embodiment of the present invention is applied; if the sales user who applies the embodiment of the invention is a user selling clothes, a sales conversation for selling clothes with a larger proportion can be adopted; the specific proportion can be set by the technicians in the field according to experience, and can be adjusted according to the sales effect after the sales prompt information is provided.
In one exemplary embodiment, the sales dialog used to construct the Markov decision process may contain only sales dialogs for one commodity; the category of the sales conversation may be a category of goods sold by the sales user to which the embodiment of the present invention is applied; for example, if the sales user is a user selling clothing, the sales dialog for constructing the markov decision process is the sales dialog for selling clothing;
in an exemplary embodiment, the sales dialog may include sales dialogs of sales users of a plurality of different sales levels, the sales dialogs including both sales successful dialogs and sales failed dialogs.
In an exemplary embodiment, the sales dialog may be in a format that includes: video, audio, or text; to construct the markov decision process, the sales dialog, which is not in the text format, needs to be converted into the text format, and text-formatted dialog information used for constructing the markov decision process is generated based on the conversion, for example, before obtaining the dialog information, information included in the sales dialog may be recognized by using an Automatic Speech Recognition (ASR) technique, a text-formatted file is generated, and after the text-formatted file is parsed and generated, dialog information of a preset dialog state is obtained.
In an exemplary embodiment, the dialog states include, but are not limited to:
the status of the customer in one or any combination of the following: the method comprises the following steps of providing demand, providing a question, providing an auction product, consulting price, consulting preferential, consulting after-sale, determining transaction, rejecting transaction and the like;
the status of the sales user of one or any combination of: welcome, demand communication, recommendation, question answering, brand introduction, preferential content, guest situation, contact information acquisition and the like.
It should be noted that the dialog state in the embodiment of the present invention may be obtained by parsing a set model or rule based on a text analysis method in the related art.
The building unit is used for: constructing a Markov decision process based on the dialogue information which is obtained by analysis and contains each dialogue state;
in one exemplary embodiment, the expression of the markov decision process is < S, a, P, R, γ >;
wherein, the expression < S, A, P, R, Gamma > is as follows: s is a conversation information set of each conversation state of a customer, A is a conversation information set of each conversation state of a sales user, P is a state transition matrix in which the conversation states of the customer are transitioned, R is a preset reward value of the conversation state, and gamma is a preset reward attenuation coefficient corresponding to the reward value; the state transition matrix includes: each conversation state of the sales user causes a transition state in which the conversation state of the customer transitions, and transition probabilities corresponding to the respective transition states.
In an exemplary embodiment, the reward value for the dialog state may be set according to the following rules:
the reward value for the session state that completes the transaction is 1, the reward value for the session state that rejects the transaction is-1, and the reward values for the other session states are 0.
In an exemplary embodiment, the value range of the reward attenuation coefficient is 0-1, and can be set by experience values of those skilled in the art, and the closer the reward attenuation coefficient is to 1, the more deliberate return can be represented.
The prompting unit is used for: providing real-time dialogue prompt information for a selling user through a constructed Markov decision process;
in an exemplary embodiment, the prompting unit is specifically configured to:
and according to the Markov decision process, feeding back the conversation state of the next conversation with the customer to the sales user in real time.
In an exemplary embodiment, an apparatus of an embodiment of the present invention further includes an updating unit, configured to:
and updating the constructed Markov decision process according to the newly added sales dialogue.
The embodiment of the invention can provide more accurate sales prompt information for the sales user through the iterative update of the newly added sales dialogue.
Compared with the related art, the technical scheme of the application comprises the following steps: analyzing the sales conversation of a preset number of commodities to obtain conversation information containing two or more preset conversation states; constructing a Markov decision process based on the dialogue information which is obtained by analysis and contains each dialogue state; providing real-time dialogue prompt information for a selling user through a constructed Markov decision process; wherein the sales conversation comprises: a conversation between the sales user and the customer. The embodiment of the invention provides conversation prompt information for the real-time sale of the selling user and provides information support for improving the sale level of the selling user through the Markov decision process constructed based on the sale conversation.
The embodiment of the invention also provides a computer storage medium, wherein a computer program is stored in the computer storage medium, and when being executed by a processor, the computer program realizes the method for realizing the information processing.
An embodiment of the present invention further provides a terminal, including: a memory and a processor, the memory having a computer program stored therein; wherein the content of the first and second substances,
the processor is configured to execute the computer program in the memory;
the computer program, when executed by the processor, implements a method of implementing information processing as described above.
It will be understood by those of ordinary skill in the art that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
Claims (10)
1. A method of implementing information processing, comprising:
analyzing the sales conversation of a preset number of commodities to obtain conversation information containing two or more preset conversation states;
constructing a Markov decision process based on the dialogue information which is obtained by analysis and contains each dialogue state;
providing real-time dialogue prompt information for a selling user through a constructed Markov decision process;
wherein the sales conversation comprises: a conversation between the sales user and the customer.
2. The method of claim 1, wherein the dialog state comprises:
the status of the customer in one or any combination of the following: the method comprises the following steps of providing demand, providing a question, providing an auction product, consulting price, consulting preferential, consulting after-sale, determining transaction and rejecting transaction;
the status of the sales user of one or any combination of: welcome, demand communication, recommendation, question answering, brand introduction, preferential content, guest situation and contact information acquisition.
3. The method of claim 1, wherein the Markov decision process is expressed as < S, A, P, R, γ >;
wherein, the expression < S, A, P, R, Gamma > is as follows: s is a conversation information set of each conversation state of a customer, A is a conversation information set of each conversation state of a sales user, P is a state transition matrix in which the conversation states of the customer are transitioned, R is a preset reward value of the conversation state, and gamma is a preset reward attenuation coefficient corresponding to the reward value; the state transition matrix includes: each conversation state of the sales user causes a transition state in which the conversation state of the customer transitions, and transition probabilities corresponding to the respective transition states.
4. The method according to any one of claims 1 to 3, wherein the providing of the real-time dialog prompt information for the selling user comprises:
and according to the Markov decision process, feeding back the conversation state of the next conversation with the customer to the sales user in real time.
5. An apparatus for implementing information processing, comprising: the device comprises an analysis unit, a construction unit and a prompt unit; wherein the content of the first and second substances,
the analysis unit is used for: analyzing the sales conversation of a preset number of commodities to obtain conversation information containing two or more preset conversation states;
the building unit is used for: constructing a Markov decision process based on the dialogue information which is obtained by analysis and contains each dialogue state;
the prompting unit is used for: providing real-time dialogue prompt information for a selling user through a constructed Markov decision process;
wherein the sales conversation comprises: a conversation between the sales user and the customer.
6. The apparatus of claim 5, wherein the dialog state comprises:
the status of the customer in one or any combination of the following: the method comprises the following steps of providing demand, providing a question, providing an auction product, consulting price, consulting preferential, consulting after-sale, determining transaction and rejecting transaction;
the status of the sales user of one or any combination of: welcome, demand communication, recommendation, question answering, brand introduction, preferential content, guest situation and contact information acquisition.
7. The apparatus of claim 5, wherein the Markov decision process is expressed as < S, A, P, R, γ >;
wherein, the expression < S, A, P, R, Gamma > is as follows: s is a conversation information set of each conversation state of a customer, A is a conversation information set of each conversation state of a sales user, P is a state transition matrix in which the conversation states of the customer are transitioned, R is a preset reward value of the conversation state, and gamma is a preset reward attenuation coefficient corresponding to the reward value; the state transition matrix includes: each conversation state of the sales user causes a transition state in which the conversation state of the customer transitions, and transition probabilities corresponding to the respective transition states.
8. The device according to any one of claims 5 to 7, wherein the prompting unit is specifically configured to:
and the sales user feeds back the conversation state of the next conversation with the customer to the sales user in real time according to the Markov decision process.
9. A computer storage medium having stored therein a computer program which, when executed by a processor, implements a method of implementing information processing as claimed in any one of claims 1 to 4.
10. A terminal, comprising: a memory and a processor, the memory having a computer program stored therein; wherein the content of the first and second substances,
the processor is configured to execute the computer program in the memory;
the computer program, when executed by the processor, implements a method of implementing information processing as recited in any of claims 1-4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911052314.5A CN110796495A (en) | 2019-10-31 | 2019-10-31 | Method, device, computer storage medium and terminal for realizing information processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911052314.5A CN110796495A (en) | 2019-10-31 | 2019-10-31 | Method, device, computer storage medium and terminal for realizing information processing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110796495A true CN110796495A (en) | 2020-02-14 |
Family
ID=69442341
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911052314.5A Pending CN110796495A (en) | 2019-10-31 | 2019-10-31 | Method, device, computer storage medium and terminal for realizing information processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110796495A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112579758A (en) * | 2020-12-25 | 2021-03-30 | 北京百度网讯科技有限公司 | Model training method, device, equipment, storage medium and program product |
CN114500425A (en) * | 2022-01-25 | 2022-05-13 | 上海禹璨信息技术有限公司 | Information processing method, device, equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140039979A1 (en) * | 2012-08-01 | 2014-02-06 | Opera Solutions, Llc | System and Method for Demand Forecasting |
CN108234785A (en) * | 2018-01-16 | 2018-06-29 | 平安科技(深圳)有限公司 | Telemarketing reminding method, electronic device and readable storage medium storing program for executing |
CN110060098A (en) * | 2019-04-04 | 2019-07-26 | 秒针信息技术有限公司 | The acquisition methods and device of marketing term |
-
2019
- 2019-10-31 CN CN201911052314.5A patent/CN110796495A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140039979A1 (en) * | 2012-08-01 | 2014-02-06 | Opera Solutions, Llc | System and Method for Demand Forecasting |
CN108234785A (en) * | 2018-01-16 | 2018-06-29 | 平安科技(深圳)有限公司 | Telemarketing reminding method, electronic device and readable storage medium storing program for executing |
CN110060098A (en) * | 2019-04-04 | 2019-07-26 | 秒针信息技术有限公司 | The acquisition methods and device of marketing term |
Non-Patent Citations (1)
Title |
---|
鲁科烃: "基于样本增强的强化学习在对话管理中的应用", 《中国知网》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112579758A (en) * | 2020-12-25 | 2021-03-30 | 北京百度网讯科技有限公司 | Model training method, device, equipment, storage medium and program product |
CN114500425A (en) * | 2022-01-25 | 2022-05-13 | 上海禹璨信息技术有限公司 | Information processing method, device, equipment and storage medium |
CN114500425B (en) * | 2022-01-25 | 2023-05-02 | 上海禹璨信息技术有限公司 | Information processing method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107391750B (en) | Method and apparatus for processing information | |
CN109218390B (en) | User screening method and device | |
US10580012B2 (en) | Article-suggestion system for automatically resolving customer-service requests | |
CN110796495A (en) | Method, device, computer storage medium and terminal for realizing information processing | |
CN111178940A (en) | Method and system for automatically generating sales call technology map | |
CN113535991A (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
CN109033285A (en) | Information-pushing method and device | |
US11361754B2 (en) | Method and system for speech effectiveness evaluation and enhancement | |
CN117057762A (en) | Position information processing method, device, equipment and storage medium based on AI | |
US20230154113A1 (en) | Dynamic avatars for customer support applications | |
CN111414764A (en) | Method and system for determining skill field of dialog text | |
KR102327011B1 (en) | Method and apparatus for enhancing consultation service quality | |
CN112818689B (en) | Entity identification method, model training method and device | |
CN111276020A (en) | Question-answer interaction system and method for online education platform | |
CN115630152A (en) | Virtual character live conversation mode, device, electronic equipment and storage medium | |
US20230222449A1 (en) | Online Interview Method and System | |
CN113010664B (en) | Data processing method and device and computer equipment | |
CN110798393A (en) | Voiceprint bubble display method and terminal using voiceprint bubbles | |
CN110516043B (en) | Answer generation method and device for question-answering system | |
CN115392943A (en) | Method, device, equipment and storage medium for sending display information | |
CN111935363A (en) | Call routing method and system | |
CN109726267A (en) | Story recommended method and device for Story machine | |
CN114095738A (en) | Video and live broadcast processing method, live broadcast system, electronic device, terminal and medium | |
CN113468297B (en) | Dialogue data processing method and device, electronic equipment and storage equipment | |
CN115907272B (en) | Method and device for evaluating brokers, electronic equipment 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200214 |
|
RJ01 | Rejection of invention patent application after publication |